© 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. 38790
    Prev
    Next
    INDEX
    Explanations

    object definitions

    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
     POD
    -0.07
    铄
    -0.07
     CONST
    -0.07
     Conditional
    -0.07
    晨
    -0.07
    LLL
    -0.07
     Hermes
    -0.07
    จ
    -0.07
    Boolean
    -0.07
    터
    -0.07
    POSITIVE LOGITS
    .hl
    0.07
    .MIN
    0.07
    しく
    0.07
    ᄒ
    0.07
    幫
    0.07
    nton
    0.06
    .popup
    0.06
    aliases
    0.06
    checker
    0.06
    atinum
    0.06
    Activations Density 0.003%

    No Known Activations