© 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. 18202
    Prev
    Next
    INDEX
    Explanations

    T

    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
    neau
    -0.27
    åıijå±ķæł¼å±Ģ
    -0.25
    åĭĭç«ł
    -0.25
    æĦŁ
    -0.25
     PSP
    -0.24
    otel
    -0.24
    æĭĵ
    -0.23
    å¼ĢæĿ¥
    -0.23
    ç½ķ
    -0.23
     nostr
    -0.23
    POSITIVE LOGITS
    Across
    0.28
    urai
    0.27
    ilage
    0.26
    ty
    0.26
    åijĬè¯īä»ĸ
    0.25
     crossed
    0.25
    ARN
    0.25
    Êģ
    0.25
     <![
    0.25
     Across
    0.25
    Activations Density 0.006%

    No Known Activations