© 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. 18267
    Prev
    Next
    INDEX
    Explanations

    first of all

    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
    лаÑĤÑĭ
    -0.07
    ukup
    -0.07
    /*@
    -0.07
    ç§ijåѦä¸İ
    -0.07
    Witness
    -0.07
    èĢĮåĬªåĬĽ
    -0.07
    åıªèĥ½è¯´
    -0.07
    ëĮĢìĻĢ
    -0.07
    áĢ±áĢ¸
    -0.07
     Daly
    -0.07
    POSITIVE LOGITS
    iran
    0.07
    rts
    0.06
    ä½Ĩä¹Ł
    0.06
    æİīçļĦ
    0.06
    .nz
    0.06
    olv
    0.06
    enton
    0.06
     вÑĭÑĢÑĥ
    0.06
    èĩ³å°Ĭ
    0.06
    ä½Ĩèĭ¥
    0.06
    Activations Density 0.273%

    No Known Activations