© 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. 95777
    Prev
    Next
    INDEX
    Explanations

    header

    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
    头
    -1.35
     head
    -1.30
     heads
    -1.26
     Head
    -1.21
    head
    -1.17
    Head
    -1.13
    heads
    -1.09
    头éĥ¨
    -1.09
    éłŃ
    -1.09
    _head
    -1.07
    POSITIVE LOGITS
    lein
    0.26
    nameof
    0.25
    FINE
    0.24
    éģ²
    0.24
     Sight
    0.22
    chants
    0.22
    æľ¬æĬ¥è®°èĢħ
    0.22
     anale
    0.22
    lesh
    0.22
    è¿ŁåĪ°
    0.21
    Activations Density 0.987%

    No Known Activations