© 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. 38782
    Prev
    Next
    INDEX
    Explanations

    good or bad

    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
    欢声
    -0.09
    emark
    -0.08
    âng
    -0.08
    èĩªè¨Ģ
    -0.08
     nieu
    -0.08
    ceaux
    -0.07
    æ°¨éħ¸
    -0.07
    ereien
    -0.07
    мли
    -0.07
    idité
    -0.07
    POSITIVE LOGITS
     worth
    0.09
     ÙĪØ£ÙĨÙĩ
    0.08
    åĪĻ认为
    0.08
    å°±åºĶ该
    0.08
     inherently
    0.08
    åij½ä¸Ń
    0.08
    éĥ½åĢ¼å¾Ĺ
    0.08
     ÑıкобÑĭ
    0.07
    å¿ħæľī
    0.07
    å¿ħ
    0.07
    Activations Density 0.177%

    No Known Activations