© 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. 7-RESID-POST-AA
    11. 41039
    Prev
    Next
    INDEX
    Explanations

    establishment

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    浒
    -0.07
     Granny
    -0.07
     sweep
    -0.07
    这篇
    -0.07
    /img
    -0.06
     Amateur
    -0.06
    ($('<
    -0.06
    自学
    -0.06
     العرا
    -0.06
    สะ
    -0.06
    POSITIVE LOGITS
    发生
    0.08
     confirmed
    0.08
    _LE
    0.08
    ключ
    0.07
    _ACCESS
    0.07
    𓇼
    0.07
     creations
    0.07
    却发现
    0.07
    lo
    0.07
    wel
    0.07
    Activations Density 0.014%

    No Known Activations