© 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. 45325
    Prev
    Next
    INDEX
    Explanations

    compute or calculate

    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
    ÑģÑĤане
    -0.08
    regor
    -0.07
    ë³Ģ
    -0.07
     запо
    -0.07
    æľ¬æĸĩ为
    -0.07
    emel
    -0.07
    vig
    -0.07
    ł
    -0.07
    åĨįåĬłä¸Ĭ
    -0.07
    пе
    -0.07
    POSITIVE LOGITS
    ç¼Ń
    0.08
    ENCH
    0.07
    ESC
    0.07
    atar
    0.07
    lesc
    0.07
    èĸ°
    0.07
    ATAR
    0.07
    _special
    0.07
    lashes
    0.06
    Ùħز
    0.06
    Activations Density 0.029%

    No Known Activations