© 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. 19-RESID-POST-AA
    11. 75079
    Prev
    Next
    INDEX
    Explanations

    announcements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     full
    -0.07
    Accounts
    -0.06
    Minor
    -0.06
     Pulse
    -0.06
     Applications
    -0.06
    好不容易
    -0.06
    Ay
    -0.06
     Los
    -0.06
    大人
    -0.06
    optional
    -0.06
    POSITIVE LOGITS
     الشر
    0.08
     zug
    0.07
     demonstrates
    0.07
    檩
    0.07
    getField
    0.07
     Creation
    0.07
    confirmed
    0.07
     xa
    0.07
     SHALL
    0.07
     rides
    0.07
    Activations Density 0.056%

    No Known Activations