© 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. 129996
    Prev
    Next
    INDEX
    Explanations

    of

    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
    æµħ
    -0.26
    lock
    -0.25
     hypoc
    -0.25
    $action
    -0.25
    -fluid
    -0.25
     overs
    -0.24
    åĤij
    -0.24
     shallow
    -0.23
    æĻ·
    -0.23
     comparison
    -0.23
    POSITIVE LOGITS
    .rawValue
    0.28
    å·¥ä¸ļ大åѦ
    0.26
    utor
    0.25
    amina
    0.25
    åħŃåIJĪ
    0.24
    -transitional
    0.24
    CCA
    0.24
    isphere
    0.23
    ENA
    0.23
    AAC
    0.23
    Activations Density 2.123%

    No Known Activations