© 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. 95708
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    èģĺ
    -0.31
    浸
    -0.30
    avigator
    -0.28
     perennial
    -0.27
    为大家
    -0.25
    itori
    -0.24
    venues
    -0.24
    হ
    -0.24
    ä¸Ģç»ı
    -0.24
    åħ·
    -0.24
    POSITIVE LOGITS
    instanc
    0.29
    -uppercase
    0.25
    -FIRST
    0.25
    _stdio
    0.25
    -percent
    0.24
    acier
    0.24
    æĬ¥åijĬæĺ¾ç¤º
    0.24
    ByExample
    0.23
     Earlier
    0.23
     contradictory
    0.23
    Activations Density 0.888%

    No Known Activations

    This feature has no known activations.