© 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. 27155
    Prev
    Next
    INDEX
    Explanations

    academic assignments and tests

    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
    æĺ¾èijĹçļĦ
    -0.08
    roker
    -0.08
    ÑģÑģоÑĢ
    -0.08
    .interval
    -0.08
    ĵ¨
    -0.08
    akter
    -0.07
    éģĵéģĵ
    -0.07
    setError
    -0.07
    为主ä½ĵ
    -0.07
    .NewReader
    -0.07
    POSITIVE LOGITS
    æĪĸ个人
    0.07
     or
    0.07
    -like
    0.07
    -friendly
    0.06
    æĪĸ
    0.06
    /
    0.06
    级çļĦ
    0.06
    ëĤĺ
    0.06
    /group
    0.06
    ized
    0.06
    Activations Density 0.011%

    No Known Activations