© 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. 17402
    Prev
    Next
    INDEX
    Explanations

    adaptive staircaseagain made

    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
     diss
    -0.08
    CONN
    -0.07
    iloc
    -0.07
    conn
    -0.07
    pike
    -0.06
    è¿ŀæİ¥åĪ°
    -0.06
    æĥħåĨµåĪĨæŀIJ
    -0.06
    æľīç»Ħç»ĩ
    -0.06
    è¿ŀæİ¥çļĦ
    -0.06
     dang
    -0.06
    POSITIVE LOGITS
    èĥĨåŃIJ
    0.08
    _LOWER
    0.08
     Narrow
    0.08
    меÑĢи
    0.08
    æĹ©æĹ¥
    0.08
    iby
    0.07
    åĮºéĹ´
    0.07
    Range
    0.07
    bile
    0.07
    ÙĨج
    0.07
    Activations Density 0.002%

    No Known Activations