© 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. 32-TRANSCODER-HP
    7. 42186
    Prev
    Next
    INDEX
    Explanations

    Non-English characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĪ¸çĪ¸å¦Īå¦Ī
    -0.28
    èĥĸ
    -0.26
    纵
    -0.26
    縱
    -0.26
     dads
    -0.26
    sem
    -0.26
    èłķ
    -0.26
     ÐijеÑģ
    -0.26
    odelist
    -0.26
    -parent
    -0.25
    POSITIVE LOGITS
    qu
    0.28
     пÑĢоиз
    0.27
    KHTML
    0.26
    ä½Ļé¢Ŀ
    0.26
    éĿĴå¹´
    0.26
    è¡¨æł¼
    0.26
    illin
    0.25
    æµ·æĭĶ
    0.25
     getProduct
    0.24
     queda
    0.24
    Activations Density 0.000%

    No Known Activations