© 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. 29647
    Prev
    Next
    INDEX
    Explanations

    RETURNS

    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
    åľ¨ä¸Ģèµ·çļĦ
    -0.09
    è¿ĩæĿ¥çļĦ
    -0.08
    è¿Ļæł·çļĦè¯Ŀ
    -0.08
    åĩºåİ»çļĦ
    -0.08
    éĹ®é¢ĺçļĦ
    -0.08
    äºĨçļĦ
    -0.08
    åĽŀæĿ¥çļĦ
    -0.08
    æķĪæŀľçļĦ
    -0.08
    å¾Īé«ĺçļĦ
    -0.07
    åĽŀ家çļĦ
    -0.07
    POSITIVE LOGITS
    èĻ½æľī
    0.08
    åİĭåĬĽå¤§
    0.07
    åĽłç´łå½±åĵį
    0.07
    åĿĩå±ŀ
    0.07
    èĻ½
    0.07
    æĪijåIJĥ
    0.07
    并äºİ
    0.07
    ä¸Ģæĥ³åĪ°
    0.07
    为维æĬ¤
    0.06
    æĤīæķ°
    0.06
    Activations Density 0.003%

    No Known Activations