© 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. 24454
    Prev
    Next
    INDEX
    Explanations

    some, many, much, frequently, often

    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
    °
    -0.08
     somehow
    -0.07
    羣æŃ£
    -0.07
    acci
    -0.07
    urre
    -0.07
     truly
    -0.06
    ember
    -0.06
     except
    -0.06
     Except
    -0.06
    éĢļ常æĥħåĨµä¸ĭ
    -0.06
    POSITIVE LOGITS
    ä¸įä¸Ģå®ļæĺ¯
    0.09
    ä¸įä¸Ģå®ļ
    0.09
    noinspection
    0.08
    ä½Ĩä¹Łæľī
    0.08
    ánÃŃ
    0.08
    SEL
    0.08
    ä¸įåħį
    0.08
    iems
    0.08
    fois
    0.08
    æĪ·æĻĵ
    0.08
    Activations Density 0.283%

    No Known Activations