© 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. 45797
    Prev
    Next
    INDEX
    Explanations

    first month

    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
    å¸Ĩ
    -0.07
    èĭ±æĸĩåIJįåŃĹ
    -0.06
    ëłĪìĿ´
    -0.06
     Bellev
    -0.06
    æĵ¬
    -0.06
    èĬĤ
    -0.06
    ket
    -0.06
    åħ³éĹŃçªĹåı£
    -0.06
    æľ¬æ¥¼
    -0.06
    oom
    -0.06
    POSITIVE LOGITS
    å¿ħè¦ģæĿ¡ä»¶
    0.10
    以ä¸ĭæĿ¡ä»¶
    0.09
    åIJĮæŶè¿ĺè¦ģ
    0.08
    åIJĮæĹ¶ä¹Łè¦ģ
    0.08
    åĪ¤åĪ«
    0.08
     additionally
    0.08
    issen
    0.08
    åŁºæľ¬æĿ¡ä»¶
    0.07
    æīįèĥ½ä¿Ŀè¯ģ
    0.07
    CharacterSet
    0.07
    Activations Density 0.001%

    No Known Activations