© 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. 19-RESID-POST-AA
    11. 7493
    Prev
    Next
    INDEX
    Explanations

    numerical data

    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
    =\"%
    -0.07
    hevik
    -0.07
     jos
    -0.07
    進一步
    -0.07
    ="-
    -0.07
    成为中国
    -0.06
     พฤษภาคม
    -0.06
    setText
    -0.06
     encuentra
    -0.06
    榍
    -0.06
    POSITIVE LOGITS
    bull
    0.08
    所提供的
    0.07
    .Parcel
    0.07
    学前教育
    0.07
     incoming
    0.07
     Needs
    0.07
     Hire
    0.07
     A
    0.07
    *self
    0.07
     assessing
    0.07
    Activations Density 0.068%

    No Known Activations