© 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. 30-TRANSCODER-HP
    7. 95752
    Prev
    Next
    INDEX
    Explanations

    Code snippets and technical text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Areas
    -0.28
    .neo
    -0.27
     cyt
    -0.27
    æĿĨèıĮ
    -0.26
    /topic
    -0.25
    emain
    -0.25
     cuffs
    -0.24
    arms
    -0.24
    Synopsis
    -0.24
    eur
    -0.23
    POSITIVE LOGITS
    åīª
    0.30
    缮
    0.27
     sĩ
    0.26
    åĪĽæĸ°èĥ½åĬĽ
    0.26
     societies
    0.25
    WISE
    0.25
    ç»Īç»ĵ
    0.25
     structures
    0.24
    社
    0.24
     Pis
    0.24
    Activations Density 0.103%

    No Known Activations