© 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. 47901
    Prev
    Next
    INDEX
    Explanations

    how to improve

    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
    æķ¢
    -0.08
     general
    -0.07
    ä¸ĢèĪ¬æĥħåĨµä¸ĭ
    -0.07
    强çĥĪ
    -0.07
     prefers
    -0.07
     ÙĬÙģضÙĦ
    -0.07
     generally
    -0.07
    å®ģæĦ¿
    -0.07
    åĢ¾åIJijäºİ
    -0.07
    åİŁåĪĻä¸Ĭ
    -0.06
    POSITIVE LOGITS
    å¦Ĥä½ķéĢļè¿ĩ
    0.13
    å°±æĺ¯éĢļè¿ĩ
    0.12
    éĢļè¿ĩå°Ĩ
    0.11
    以ä¸ĭæĸ¹å¼ı
    0.11
    éĢļè¿ĩè¿ĻäºĽ
    0.10
    ãģ©ãģ®ãĤĪãģĨãģ«
    0.10
    éĢļè¿ĩåľ¨
    0.10
    æĪij们éĢļè¿ĩ
    0.10
    éĢļè¿ĩä¸İ
    0.10
    æĺ¯éĢļè¿ĩ
    0.10
    Activations Density 0.028%

    No Known Activations