© 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. 60159
    Prev
    Next
    INDEX
    Explanations

    units after slashes

    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
    ias
    -0.07
    afil
    -0.07
    æ¡Įä¸ĬçļĦ
    -0.06
    -La
    -0.06
    Ñħи
    -0.06
    ikian
    -0.06
    IFY
    -0.06
    åľ¨ä¸»
    -0.06
    es
    -0.06
    åı¹æ°Ķ
    -0.06
    POSITIVE LOGITS
    Unnamed
    0.08
     capita
    0.07
    /vnd
    0.07
     Schönh
    0.07
     unr
    0.07
    çĹĽå¿«
    0.07
    Ùijع
    0.07
    à®Łà¯įà®ļ
    0.07
    _unused
    0.07
    æĸ°å¤©åľ°
    0.07
    Activations Density 0.007%

    No Known Activations