© 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. 19046
    Prev
    Next
    INDEX
    Explanations

    the

    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
     Life
    -0.31
     life
    -0.31
    life
    -0.31
    Life
    -0.29
    çĶŁæ´»
    -0.29
    æĬ¥
    -0.29
    æĬ¥åijĬæĺ¾ç¤º
    -0.28
     LIFE
    -0.28
    人çĶŁ
    -0.28
    _report
    -0.27
    POSITIVE LOGITS
    thin
    0.27
    è½®
    0.26
     Meteor
    0.26
    åĩ¤åĩ°
    0.26
    eil
    0.25
     weather
    0.24
    嫦
    0.24
    åħħå®ŀ
    0.24
    planet
    0.24
    bullet
    0.24
    Activations Density 0.146%

    No Known Activations