© 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. 8663
    Prev
    Next
    INDEX
    Explanations

    numbers and names

    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
    ardin
    -0.07
    enius
    -0.06
     ill
    -0.06
    arat
    -0.06
    ä¸īåĨľ
    -0.06
    ÑģÑĤеÑĢа
    -0.06
    okes
    -0.06
    cv
    -0.06
    waard
    -0.06
    _USAGE
    -0.06
    POSITIVE LOGITS
    ÚĨار
    0.07
    erre
    0.07
     herr
    0.07
    ével
    0.07
    åij¨è¾¹
    0.07
    _PLACE
    0.07
    ç½ķ
    0.07
    estination
    0.07
    éĽ
    0.07
    è¿ĻäºĽå¹´
    0.07
    Activations Density 0.009%

    No Known Activations