© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 129059
    Prev
    Next
    INDEX
    Explanations

    technology and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     SWITCH
    -0.30
    icens
    -0.28
    åĽ¢ä½ĵ
    -0.28
    USTER
    -0.26
     Nichols
    -0.26
    flen
    -0.26
     Bars
    -0.25
    ENDED
    -0.25
    IENT
    -0.24
    OOK
    -0.24
    POSITIVE LOGITS
    om
    0.27
    Assignable
    0.26
    大éģĵ
    0.25
    seau
    0.25
    ing
    0.25
     judgment
    0.25
    è£ı
    0.25
     yourself
    0.24
    atÄĥ
    0.24
    ingly
    0.24
    Activations Density 0.035%

    No Known Activations