© 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. 62256
    Prev
    Next
    INDEX
    Explanations

    generic type wildcards

    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
    -0.06
    åݿ人
    -0.06
    аÑĩ
    -0.06
    ’t
    -0.06
     cualquiera
    -0.06
    اÙĨÙĩ
    -0.06
    ÅĻ
    -0.06
    lic
    -0.06
    abet
    -0.06
    çİĩè¾¾
    -0.06
    POSITIVE LOGITS
    -comments
    0.09
    iaux
    0.08
    anders
    0.08
    gom
    0.08
    æ¯ĵ
    0.08
    ZI
    0.08
    [__
    0.08
    âĢ¥
    0.08
    unto
    0.08
     Cosby
    0.07
    Activations Density 0.023%

    No Known Activations