© 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. 31578
    Prev
    Next
    INDEX
    Explanations

    technical roles and systems

    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
    arka
    -0.07
    onner
    -0.07
    atty
    -0.07
    ÙĬÙĩ
    -0.07
    èĩªéĢī
    -0.07
    ноÑģÑĤей
    -0.07
     ÑĤоÑĢмо
    -0.07
    éĺ
    -0.07
    åĽłäººèĢĮå¼Ĥ
    -0.07
    åIJĮçŃīåѦåĬĽ
    -0.07
    POSITIVE LOGITS
    æ³ķ人
    0.08
     backstage
    0.08
    è¡ĮæĶ¿
    0.07
     Staff
    0.07
    çļĦåĨħéĥ¨
    0.07
    (internal
    0.07
    \xff
    0.07
    éĢģèµ°
    0.07
     Burb
    0.07
    /Admin
    0.07
    Activations Density 0.527%

    No Known Activations