© 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. 95862
    Prev
    Next
    INDEX
    Explanations

    Weather

    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
    ãģ§ãģįãģ¦
    -0.26
    wij
    -0.25
    红线
    -0.25
    麻çĥ¦
    -0.24
    loit
    -0.24
    _red
    -0.24
    /red
    -0.23
    é»İ
    -0.23
    abile
    -0.23
    umm
    -0.23
    POSITIVE LOGITS
    icians
    0.28
    antic
    0.27
     forecast
    0.27
    åħ¥åĽŃ
    0.27
    [__
    0.26
    ician
    0.25
    ason
    0.25
    forecast
    0.25
    æľį
    0.25
    afen
    0.25
    Activations Density 0.003%

    No Known Activations