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

    Neuronpedia

    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. 15-RESID-POST-AA
    11. 84141
    Prev
    Next
    INDEX
    Explanations

    npm dependencies

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "()
    -0.07
    vu
    -0.07
    霆
    -0.07
    ⾝
    -0.07
    gni
    -0.07
    _black
    -0.07
    ꜥ
    -0.07
    géni
    -0.06
    rı
    -0.06
    gang
    -0.06
    POSITIVE LOGITS
     أبريل
    0.09
    (or
    0.08
     acept
    0.08
    造纸
    0.07
     strictly
    0.07
     еще
    0.07
     lire
    0.07
     weekly
    0.07
     roasted
    0.07
    (integer
    0.07
    Activations Density 0.002%

    No Known Activations