© 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. 27107
    Prev
    Next
    INDEX
    Explanations

    git repo name

    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
    imps
    -0.08
    oger
    -0.07
    ç¨įç¨į
    -0.07
    зина
    -0.07
    outines
    -0.07
    Delimiter
    -0.07
    åĶĨ
    -0.07
    社
    -0.07
    æį®
    -0.07
    اع
    -0.07
    POSITIVE LOGITS
    å½±å±ķ
    0.06
    ä½Ĩåĩ¡
    0.06
    ä¾Ī
    0.06
    oner
    0.06
     Pala
    0.06
    ä½łè¿ĺåľ¨
    0.06
    ç§įçĶ°
    0.06
     /**<
    0.06
    å¤ļ说
    0.06
    缴åĩ»
    0.06
    Activations Density 0.004%

    No Known Activations