© 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. 27270
    Prev
    Next
    INDEX
    Explanations

    group method

    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
    ÑģÑĤили
    -0.08
    nat
    -0.07
    åŃ°
    -0.07
    amore
    -0.07
    _doc
    -0.06
    ë°©
    -0.06
     queryParams
    -0.06
    Quan
    -0.06
    rees
    -0.06
    个人认为
    -0.06
    POSITIVE LOGITS
    æ³ķçŃī
    0.08
    æ³ķæĺ¯
    0.08
    "path
    0.08
    urgi
    0.07
    olg
    0.07
    礼åłĤ
    0.07
    аÑĢи
    0.07
    çļĦæľīåħ³
    0.07
    icum
    0.07
    (pre
    0.07
    Activations Density 0.019%

    No Known Activations