© 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. 58220
    Prev
    Next
    INDEX
    Explanations

    predatory hunting and prey

    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
    ences
    -0.10
    ç£ħ
    -0.07
    ently
    -0.07
    æ°´æ´Ĺ
    -0.07
    æ¡IJ
    -0.07
    onese
    -0.07
    ạ
    -0.07
    æĤĶ
    -0.07
    .createFrom
    -0.06
    éĿĴæĿ¾
    -0.06
    POSITIVE LOGITS
    گاÙĩ
    0.08
    /target
    0.08
    ktiv
    0.07
    INCT
    0.07
    æįķ
    0.07
    æIJľå¯»
    0.07
    æĹłæĦ§
    0.07
     Hunting
    0.07
    ogo
    0.07
    æķĪçİĩ
    0.07
    Activations Density 0.011%

    No Known Activations