© 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. 58629
    Prev
    Next
    INDEX
    Explanations

    line endings or sequences

    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¥ī
    -0.08
     rẽ
    -0.08
    éĢīåĩº
    -0.07
    éĹ¨æ§Ľ
    -0.07
    æľįè£ħ设计
    -0.07
    ingham
    -0.07
     capable
    -0.07
     horsepower
    -0.07
     renamed
    -0.07
    KeyType
    -0.07
    POSITIVE LOGITS
    indre
    0.08
     trailed
    0.08
    ä¼´ä½ł
    0.08
     trailing
    0.08
    æłĩåĩĨ为
    0.08
    Appending
    0.07
     incons
    0.07
     Ling
    0.07
    à¦ĵয়
    0.07
    æ²½
    0.07
    Activations Density 0.021%

    No Known Activations