© 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. 20-TRANSCODER-HP
    7. 130104
    Prev
    Next
    INDEX
    Explanations

    Code/technical notations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _prefix
    -0.31
    表述
    -0.28
     prefixed
    -0.27
    edes
    -0.26
    以åIJİ
    -0.25
    鼷éĶĭ
    -0.25
     preceded
    -0.25
    æ¸
    -0.25
    -prefix
    -0.24
    IJľç´¢
    -0.24
    POSITIVE LOGITS
     mit
    0.27
    åı¯ä»¥çĽ´æİ¥
    0.27
    iT
    0.27
    çļĦåij½è¿IJ
    0.26
     Tam
    0.25
    SENT
    0.25
     pinch
    0.24
    sent
    0.24
     Clamp
    0.24
     vern
    0.24
    Activations Density 36.331%

    No Known Activations