© 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. 6681
    Prev
    Next
    INDEX
    Explanations

    Subspecies/cultivar

    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
    lib
    -0.26
    oire
    -0.25
     tread
    -0.25
    tics
    -0.24
    libs
    -0.24
    odom
    -0.23
    IFORM
    -0.23
    ovel
    -0.23
    ough
    -0.23
    .GPIO
    -0.23
    POSITIVE LOGITS
    롯
    0.27
    æĿ¥åĽŀ
    0.25
    为é¦ĸçļĦ
    0.24
    åIJĦç§įåIJĦæł·
    0.24
    нÑģкий
    0.24
    ãģĹãģŁãĤĤãģ®
    0.24
    åı¼
    0.23
    çݺ
    0.23
    iese
    0.23
     hell
    0.23
    Activations Density 0.008%

    No Known Activations