© 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. 14626
    Prev
    Next
    INDEX
    Explanations

    quantities of

    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
    ä¸İä¿¡æģ¯
    -0.06
     Schultz
    -0.06
    azzi
    -0.06
    _FILENAME
    -0.06
     arity
    -0.06
    æĹ¥çĶŁ
    -0.06
    ä¸İæĿİ
    -0.06
    onav
    -0.06
    åıĸ
    -0.06
    infl
    -0.06
    POSITIVE LOGITS
    éĩıçļĦ
    0.10
    éĢĤéĩıçļĦ
    0.09
    éĩıãģ®
    0.09
    满满çļĦ
    0.09
    ëŁīìĿĺ
    0.08
    ãģļãģ¤
    0.08
    utul
    0.08
    该款
    0.08
    สà¹Īวà¸Ļà¸Ĥà¸Ńà¸ĩ
    0.08
    使çĶ¨ä¸Ń
    0.08
    Activations Density 0.526%

    No Known Activations