© 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. 15965
    Prev
    Next
    INDEX
    Explanations

    location descriptions

    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
    endale
    -0.08
    edal
    -0.07
    aires
    -0.07
    æ¯ıæľŁ
    -0.07
    ToList
    -0.07
    hib
    -0.07
    irut
    -0.07
    elaar
    -0.07
    itemap
    -0.07
    _pag
    -0.07
    POSITIVE LOGITS
    碩
    0.08
    vely
    0.07
    urgi
    0.07
    ro
    0.07
    åݲ
    0.07
    âĢ¦but
    0.06
    çĨł
    0.06
    жание
    0.06
    á»ĥn
    0.06
     intern
    0.06
    Activations Density 0.003%

    No Known Activations