© 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. 57275
    Prev
    Next
    INDEX
    Explanations

    decimal places

    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
    il
    -0.07
    æķŀ
    -0.06
    lust
    -0.06
    èİī
    -0.06
    绪
    -0.06
     S
    -0.06
     sublist
    -0.05
    å¾ĹçŁ¥
    -0.05
    ed
    -0.05
    èĢIJ
    -0.05
    POSITIVE LOGITS
    áĢ¬áĢ¸
    0.08
    atici
    0.08
    缸åħ³æ³ķå¾ĭ责任
    0.08
    লà§ĩà¦ĸ
    0.08
    uple
    0.08
     tavo
    0.08
     massas
    0.08
    HCM
    0.08
    utzer
    0.08
    actal
    0.08
    Activations Density 0.008%

    No Known Activations