© 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. 19-TRANSCODER-HP
    7. 8118
    Prev
    Next
    INDEX
    Explanations

    flight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kin
    -0.33
    ello
    -0.26
    _closure
    -0.25
    lore
    -0.24
     tip
    -0.24
    RV
    -0.24
     ere
    -0.24
     Closure
    -0.23
    Well
    -0.23
    CV
    -0.23
    POSITIVE LOGITS
    iola
    0.28
    -provider
    0.27
    -suite
    0.27
     Turnbull
    0.25
     Briggs
    0.25
    affe
    0.25
    eki
    0.25
    stylesheet
    0.24
    ression
    0.24
    åģľæŃ¢
    0.24
    Activations Density 0.553%

    No Known Activations