© 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. 9520
    Prev
    Next
    INDEX
    Explanations

    CoA compounds

    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
    ëĵłì§Ģ
    -0.07
    r
    -0.07
    unki
    -0.07
    rir
    -0.06
    sb
    -0.06
    raÄį
    -0.06
    sur
    -0.06
    ron
    -0.06
     StringBuffer
    -0.06
    ønn
    -0.06
    POSITIVE LOGITS
    eres
    0.08
    à¸Īิ
    0.08
    æ£
    0.08
    childs
    0.07
    请äºİ
    0.07
    /hooks
    0.07
    stdarg
    0.07
    аÑģÑĭ
    0.06
    andidates
    0.06
     verge
    0.06
    Activations Density 0.024%

    No Known Activations