© 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. 20-TRANSCODER-HP
    7. 108492
    Prev
    Next
    INDEX
    Explanations

    is, are, has, have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĭĻ
    -0.29
    /fs
    -0.25
     kra
    -0.24
     capitals
    -0.24
    terior
    -0.24
    amation
    -0.24
    plan
    -0.24
    fahren
    -0.23
    ÄĦ
    -0.23
    Eval
    -0.23
    POSITIVE LOGITS
    utton
    0.25
    çļĦè§Ĵèī²
    0.25
    ramid
    0.25
    outh
    0.25
    è£ķ
    0.25
    makt
    0.25
    èµİ
    0.24
    receipt
    0.24
    éĹ¨ç¥¨
    0.24
    æķĻç»ĥ
    0.24
    Activations Density 14.123%

    No Known Activations