© 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. 2871
    Prev
    Next
    INDEX
    Explanations

    error or fix

    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¸ĬéĿ¢
    -0.07
     걸
    -0.07
    æĬĬè¿ĻäºĽ
    -0.06
    对è¿ĻäºĽ
    -0.06
    æ²»
    -0.06
    asy
    -0.06
    æĺ¾å¾Ĺå¾Ī
    -0.06
    OfType
    -0.06
     little
    -0.06
    ât
    -0.06
    POSITIVE LOGITS
    reason
    0.08
    å¿ĺä¸įäºĨ
    0.08
    åħ¬åı¸æĢ»ç»ıçIJĨ
    0.07
    å·²éĢļè¿ĩ
    0.07
    ä¸Ģè§ģ
    0.07
    Ñģанд
    0.07
    æ¯ıä¸Ģ个ç»ĨèĬĤ
    0.07
    äºĨçīĩåĪ»
    0.07
    åħ¨éĿ¢å»ºè®¾
    0.07
    æĹłåıį
    0.07
    Activations Density 0.001%

    No Known Activations