© 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. 78780
    Prev
    Next
    INDEX
    Explanations

    shallow

    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
     Chiến
    -0.07
    .padding
    -0.07
     slik
    -0.07
    backend
    -0.07
    "${
    -0.07
     Waist
    -0.07
    enedor
    -0.07
     '"+
    -0.07
    .addField
    -0.07
    elan
    -0.07
    POSITIVE LOGITS
     discoveries
    0.08
    FO
    0.07
    形
    0.07
     sham
    0.07
     shallow
    0.06
    合
    0.06
    漓
    0.06
    輛
    0.06
     SEAL
    0.06
    ître
    0.06
    Activations Density 0.002%

    No Known Activations