© 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. 95989
    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
    gef
    -0.28
    _apps
    -0.27
     krat
    -0.25
    kip
    -0.25
    è¿ĻæĦıåij³çĿĢ
    -0.24
    utorial
    -0.23
    бол
    -0.23
     moc
    -0.23
    oku
    -0.23
    ripsi
    -0.23
    POSITIVE LOGITS
    addle
    0.30
     stal
    0.26
     domestically
    0.25
     Wales
    0.25
    åĽłä¸ºæĪij们
    0.24
    æĬĺ
    0.24
     tuned
    0.24
    é½Ĭ
    0.24
    å¼¹æĢ§
    0.23
    åį¡çīĩ
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.