© 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. 34035
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and symbols

    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
     Ejem
    -0.07
    ÑĢиÑģÑĤи
    -0.06
     wom
    -0.06
    jit
    -0.06
    ilter
    -0.06
    mt
    -0.06
    åį³åı¯
    -0.06
    å¤©æ±ł
    -0.06
    æ¯Ľ
    -0.06
    ä¹ĭæĺŁ
    -0.06
    POSITIVE LOGITS
    èı²å°Ķ
    0.08
    /exp
    0.07
    abal
    0.07
    ilhar
    0.07
     kalkul
    0.07
    èĩªå·±æľī
    0.07
    å¤ļåIJĥä¸ĢäºĽ
    0.07
    arris
    0.07
     непÑĢ
    0.07
    odor
    0.07
    Activations Density 0.002%

    No Known Activations