© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39216
    Prev
    Next
    INDEX
    Explanations

    path, sweat rate, precision, charge, axis, ActionCreators, UserID

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å°±åı¯èĥ½
    -0.07
    ä¸įéĻIJ
    -0.07
    åı¯èĥ½éĢłæĪIJ
    -0.06
    ayne
    -0.06
    Pet
    -0.06
     Pet
    -0.06
    æĹłæīĢ
    -0.06
     Castello
    -0.06
    adow
    -0.06
    æĹłåºı
    -0.06
    POSITIVE LOGITS
    çIJª
    0.08
    ulton
    0.08
    ä¹ŁçĶ±
    0.07
    BufferSize
    0.07
    å®ĺæĸ¹
    0.07
     Pins
    0.07
    nid
    0.07
    ä¹Łå·²
    0.07
    ä¹Łåı¯ä»¥éĢļè¿ĩ
    0.06
    巴赫
    0.06
    Activations Density 0.001%

    No Known Activations