© 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 EvalsExportsinterp-engineNEWAPI 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. 78092
    Prev
    Next
    INDEX
    Explanations

    technical text

    np_max-act · gemini-2.0-flash
    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
     impactful
    -0.08
     nav
    -0.07
     arb
    -0.07
    	pub
    -0.07
     handles
    -0.07
    itt
    -0.07
    -su
    -0.07
     NSS
    -0.07
     관
    -0.07
    的帮助下
    -0.07
    POSITIVE LOGITS
    lahoma
    0.07
    _VOICE
    0.07
    蚲
    0.07
    -grey
    0.07
    клон
    0.07
    뱔
    0.07
    tracted
    0.07
    -destruct
    0.07
     originate
    0.06
     Calories
    0.06
    Activations Density 0.436%

    No Known Activations