© 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. 31-TRANSCODER-HP
    7. 19920
    Prev
    Next
    INDEX
    Explanations

    contract

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    妯
    -0.30
     Container
    -0.27
    (thing
    -0.27
     bpp
    -0.27
     needless
    -0.26
    è¾ħåĬ©
    -0.26
    Faces
    -0.26
    LESS
    -0.26
    VERTISE
    -0.25
    ä»Ģä¹Īåij¢
    -0.25
    POSITIVE LOGITS
     contract
    0.32
     contracts
    0.30
     grant
    0.30
    contracts
    0.29
     grants
    0.28
    -git
    0.28
    contract
    0.28
    ag
    0.27
     contracting
    0.27
    _git
    0.27
    Activations Density 0.047%

    No Known Activations