© 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. 19095
    Prev
    Next
    INDEX
    Explanations

    Code identifiers and fragments

    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
    Powered
    -0.29
    disp
    -0.29
     disp
    -0.26
    .Lib
    -0.26
    bö
    -0.25
    infra
    -0.25
     Spectrum
    -0.25
     crowned
    -0.25
     Disp
    -0.25
     purse
    -0.25
    POSITIVE LOGITS
    ifier
    0.27
    åļı
    0.27
    elin
    0.26
    ]|[
    0.26
    .lastIndexOf
    0.25
    eland
    0.25
    ization
    0.24
    æĬĹæĭĴ
    0.24
    éģĹçķĻ
    0.23
     tat
    0.23
    Activations Density 0.002%

    No Known Activations