© 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. 40717
    Prev
    Next
    INDEX
    Explanations

    long text lines

    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
    è¿·
    -0.07
    riet
    -0.07
    Õ¸ÖĤÕ¶
    -0.06
    udev
    -0.06
    à¸ķร
    -0.06
    åįķä½įåĴĮ个人
    -0.06
    çļĦé«ĺ
    -0.06
    antum
    -0.06
    à¹Ģวà¸Ńรà¹Į
    -0.06
    rup
    -0.06
    POSITIVE LOGITS
    olás
    0.07
    Alloc
    0.07
    allen
    0.07
    apun
    0.07
    bito
    0.07
    allis
    0.07
    价为
    0.07
    adrid
    0.07
    proof
    0.07
    ëį°ìĿ´
    0.07
    Activations Density 0.010%

    No Known Activations