© 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. 65327
    Prev
    Next
    INDEX
    Explanations

    SqlCommand class

    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
    ç·
    -0.06
    移
    -0.06
    è§Ĩ
    -0.06
    è§ĨåĽ¾
    -0.06
    ...
    -0.06
     {}".
    -0.06
    -%
    -0.06
    wid
    -0.06
    igger
    -0.06
    _toggle
    -0.06
    POSITIVE LOGITS
    ioni
    0.10
    æĸ°éĹ»è®°èĢħ
    0.08
    ัà¸ĩ
    0.08
    人åķĬ
    0.08
    ä¸įä½ıäºĨ
    0.08
    IVEN
    0.08
    ainless
    0.07
    inste
    0.07
    enko
    0.07
    ambre
    0.07
    Activations Density 0.001%

    No Known Activations