© 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. 63073
    Prev
    Next
    INDEX
    Explanations

    missing element

    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
    ¨
    -0.08
    uddle
    -0.07
    utch
    -0.07
    ambique
    -0.07
    /--
    -0.07
    äºĨäºĭ
    -0.07
    _ANGLE
    -0.07
    å®ļæł¼
    -0.07
    å¦Ĥåħ¶
    -0.07
    ä¸įè¾ľè´Ł
    -0.07
    POSITIVE LOGITS
    æľªè¢«
    0.10
    æ¼ı
    0.09
     outside
    0.08
    ä¸įä¸İ
    0.08
    ä¸įå±ŀäºİ
    0.08
    outside
    0.08
    没æľī被
    0.08
    空éĹ´ä¸Ń
    0.07
    ä¸įåľ¨
    0.07
     unp
    0.07
    Activations Density 0.007%

    No Known Activations