© 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. Qwen3-4B
    5. 31-TRANSCODER-HP
    7. 19465
    Prev
    Next
    INDEX
    Explanations

    scientific/technical texts

    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
    Not in Any Lists

    No Comments

    Negative Logits
     IM
    -0.29
    IM
    -0.29
    imations
    -0.28
    éĵ¢
    -0.28
    at
    -0.27
    variants
    -0.27
    VR
    -0.26
     crust
    -0.26
    å¹³çŃī
    -0.26
    atum
    -0.25
    POSITIVE LOGITS
    ampp
    0.27
     formed
    0.26
     воÑĤ
    0.25
     sliced
    0.25
     Consort
    0.25
    chemist
    0.25
     connected
    0.25
     viewed
    0.24
    æ§į
    0.24
    ç»ĻæĤ¨
    0.24
    Activations Density 1.129%

    No Known Activations