© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 59328
    Prev
    Next
    INDEX
    Explanations

    First-person perspective

    np_max-act · gemini-2.0-flash

    It detects first-person, self-referential personal narrative language (places where the writer speaks about their own experiences or opinions).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Macros
    -0.07
     DLC
    -0.06
    _PATH
    -0.06
     processed
    -0.06
     validate
    -0.06
    的事实
    -0.06
    .SE
    -0.06
     것은
    -0.06
    olg
    -0.06
    (status
    -0.06
    POSITIVE LOGITS
    Trade
    0.08
    תחושת
    0.07
    	ui
    0.07
     windy
    0.07
    מומחה
    0.07
    仙
    0.07
    imu
    0.07
    绿水
    0.07
    cov
    0.07
    vl
    0.06
    Activations Density 4.691%

    No Known Activations