© 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. 14098
    Prev
    Next
    INDEX
    Explanations

    version numbers and years

    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
     prof
    -0.07
    ัà¹Īà¸Ļ
    -0.07
     Prof
    -0.07
    ä½Ĩä¸įéĻIJäºİ
    -0.06
     Lux
    -0.06
    ¢
    -0.06
    /process
    -0.06
    轻轻æĿ¾
    -0.06
     Liber
    -0.06
    æīĵå¼Ģæīĭæľº
    -0.06
    POSITIVE LOGITS
     пеÑĢи
    0.08
    uas
    0.08
    _deps
    0.07
    yled
    0.07
    genza
    0.07
    idler
    0.07
    omens
    0.07
    iene
    0.07
    liy
    0.07
    IDL
    0.07
    Activations Density 0.001%

    No Known Activations