© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42275
    Prev
    Next
    INDEX
    Explanations

    filename extensions

    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
     parch
    -0.07
     prem
    -0.06
    çļĦè¿ĺæĺ¯
    -0.06
    åı¯èĥ½æĢ§
    -0.06
    æĿ¥å¾Ĺ
    -0.06
     fac
    -0.06
    æĿ¥çļĦ
    -0.06
    комплек
    -0.06
    online
    -0.06
     Fac
    -0.06
    POSITIVE LOGITS
    omber
    0.08
    .examples
    0.07
    .reply
    0.07
    壤
    0.07
    rosse
    0.07
    romo
    0.07
    ãĥĩãĤ£ãĥ³ãĤ°
    0.07
    menti
    0.07
    翱
    0.07
    esis
    0.07
    Activations Density 0.013%

    No Known Activations