© 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. 19502
    Prev
    Next
    INDEX
    Explanations

    2012 followed by a descriptor

    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
    utu
    -0.07
    ting
    -0.07
    ç»Ĩç»Ĩ
    -0.07
    adz
    -0.06
    è§Ĩé¢ijåı·
    -0.06
    ersp
    -0.06
    amat
    -0.06
    æıIJåįĩèĩªå·±
    -0.06
    Ư
    -0.06
    awa
    -0.06
    POSITIVE LOGITS
    ancar
    0.09
    ancock
    0.09
    edia
    0.08
    ansen
    0.08
    fri
    0.08
    تاØŃ
    0.08
    каза
    0.07
    å¸ĮæľĽå¯¹æĤ¨
    0.07
     dáng
    0.07
    eke
    0.07
    Activations Density 0.224%

    No Known Activations