© 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. 12-TRANSCODER-HP
    7. 23763
    Prev
    Next
    INDEX
    Explanations

    lead

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ify
    -0.28
    åĿļå®ļä¸į移
    -0.28
    IFY
    -0.26
    迹
    -0.26
    ifies
    -0.26
    Lng
    -0.25
    [code
    -0.25
    %S
    -0.25
    åĴĮå®ĮåĸĦ
    -0.25
    Canonical
    -0.25
    POSITIVE LOGITS
     yavaÅŁ
    0.27
     slow
    0.26
     slowed
    0.26
    éĢĢ
    0.26
     slower
    0.25
    第ä¸ĢèĬĤ
    0.25
    ç¿»è¯ij
    0.25
    æĹ¥æ¶Īæģ¯
    0.25
    æħ¢
    0.25
    -label
    0.25
    Activations Density 0.000%

    No Known Activations