© 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. 129128
    Prev
    Next
    INDEX
    Explanations

    Gumball

    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
     Estimate
    -0.07
     XT
    -0.07
    ctrl
    -0.07
     Executors
    -0.07
    نتائج
    -0.06
    منتدى
    -0.06
    TI
    -0.06
     Moms
    -0.06
    ENCY
    -0.06
     routes
    -0.06
    POSITIVE LOGITS
     emple
    0.08
     Philippines
    0.07
     ℕ
    0.07
     Gonzalez
    0.07
    \">
    0.07
     hello
    0.06
     environ
    0.06
    该院
    0.06
    𝙷
    0.06
    conexion
    0.06
    Activations Density 0.001%

    No Known Activations