© 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 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. 15-RESID-POST-AA
    11. 83309
    Prev
    Next
    INDEX
    Explanations

    snow

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .setViewport
    -0.07
    __.
    -0.07
     Hình
    -0.07
    ^{-
    -0.07
    引力
    -0.07
    Ball
    -0.07
    _c
    -0.07
    씌
    -0.07
     ABOVE
    -0.07
    _sup
    -0.07
    POSITIVE LOGITS
    Eliminar
    0.08
    graded
    0.08
    ópez
    0.07
    _allocator
    0.07
     Scanner
    0.07
    填报
    0.07
     committing
    0.07
     ingresar
    0.07
    	reset
    0.07
     boasted
    0.07
    Activations Density 0.011%

    No Known Activations