© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62859
    Prev
    Next
    INDEX
    Explanations

    U.S. Pat. No

    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
    änk
    -0.09
    _VALIDATE
    -0.08
    cimiento
    -0.08
     Redistributions
    -0.08
    anker
    -0.08
    ZIA
    -0.08
    éĻĽ
    -0.08
    ceso
    -0.08
    åħĭ森
    -0.08
    izio
    -0.07
    POSITIVE LOGITS
     isn
    0.08
    çļĦ说æ³ķ
    0.07
    åIJĹ
    0.07
    èĻ½çĦ¶åľ¨
    0.07
    ?
    0.07
    ä½Ĩå®ŀéĻħä¸Ĭ
    0.07
    èĻ½çĦ¶ä¸įæĺ¯
    0.07
    si
    0.07
     somehow
    0.07
    èĻ½çĦ¶æĺ¯
    0.07
    Activations Density 0.008%

    No Known Activations