© 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. 47453
    Prev
    Next
    INDEX
    Explanations

    Kaf, Kaf eln, Kafelnikov

    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
    æĪĸåħ¶
    -0.08
    æģ¨ä¸įå¾Ĺ
    -0.07
    èĻ½çĦ¶ä¸įæĺ¯
    -0.07
    ä¼łéĹ»
    -0.07
    pseudo
    -0.06
     implicitly
    -0.06
     pseudo
    -0.06
     possibly
    -0.06
    éĢļè¿ĩåIJĦç§į
    -0.06
    åģıåIJij
    -0.06
    POSITIVE LOGITS
    opan
    0.08
    cier
    0.08
    éĢŁåº¦æħ¢
    0.07
    Recv
    0.07
     date
    0.07
    rowable
    0.07
    kdir
    0.07
    perator
    0.07
    -fe
    0.07
    ç»Ķ
    0.07
    Activations Density 0.301%

    No Known Activations