© 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. 95942
    Prev
    Next
    INDEX
    Explanations

    plate

    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
    è´Ł
    -0.28
     conflict
    -0.28
     coefficient
    -0.27
    groupid
    -0.27
     nerve
    -0.27
     territorial
    -0.26
     conflicts
    -0.26
     moth
    -0.25
    perc
    -0.24
     hay
    -0.24
    POSITIVE LOGITS
    stores
    0.30
     Internal
    0.28
    计
    0.27
    åĨħå¤ĸ
    0.26
    è¨Ī
    0.26
    Ế
    0.26
    let
    0.26
    ernes
    0.26
    ELS
    0.26
    chron
    0.25
    Activations Density 0.112%

    No Known Activations