© 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. 141784
    Prev
    Next
    INDEX
    Explanations

    Numerical values and units

    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
     Offline
    -0.27
     offline
    -0.26
    åĴĮæľįåĬ¡
    -0.26
    æī¬
    -0.25
    æľĢåħ·
    -0.24
    uss
    -0.24
    iaux
    -0.24
    _RESOURCES
    -0.23
    lesia
    -0.23
     ca
    -0.23
    POSITIVE LOGITS
    好æĦŁ
    0.31
    ulan
    0.29
     defeating
    0.27
    åľ°æ®µ
    0.27
     contributing
    0.27
    ROWS
    0.27
    æŀķ
    0.27
    ä¹±
    0.26
    è°İ
    0.26
    TAB
    0.25
    Activations Density 17.579%

    No Known Activations