© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6785
    Prev
    Next
    INDEX
    Explanations

    Dates and times

    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
    uae
    -0.32
    BAT
    -0.27
    ylene
    -0.26
    anner
    -0.25
    set
    -0.24
    anh
    -0.24
    ella
    -0.24
    éĽĢ
    -0.23
    -su
    -0.23
    ingly
    -0.23
    POSITIVE LOGITS
    ToFront
    0.27
    fib
    0.25
    artisan
    0.24
    èĤ¤
    0.24
    åIJĮä¸Ģ个
    0.24
    ,var
    0.24
    åĨįåĬłä¸Ĭ
    0.23
    çľ¨çľ¼
    0.23
    åIJİæİĴ
    0.23
    phet
    0.22
    Activations Density 0.018%

    No Known Activations