© 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. 96179
    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
    åįģåħ«æĿ¡
    -0.30
     picnic
    -0.28
    trail
    -0.27
    窨
    -0.25
    æĪijçľģ
    -0.25
    ients
    -0.25
     pitches
    -0.25
    éģ¨
    -0.24
     setSupportActionBar
    -0.24
    èĩªæĿ¥
    -0.24
    POSITIVE LOGITS
    pedia
    0.30
    Viewer
    0.27
    yg
    0.26
    PFN
    0.26
    ä»Ħ
    0.25
    irt
    0.24
    ç»Į
    0.24
     tal
    0.24
    еп
    0.24
    [`
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.