© 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. 22516
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or code

    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
    æĪijæĿ¥è¯´
    -0.08
    جاÙħ
    -0.07
    åIJİè¿Ľ
    -0.07
    ertos
    -0.07
    _IGNORE
    -0.07
    änn
    -0.07
    ä¹ĭå®Ŀ
    -0.07
    è³ĵ
    -0.07
    ยิà¸Ļ
    -0.06
    /of
    -0.06
    POSITIVE LOGITS
    èĭ¦
    0.08
    =-=-=-=-=-=-=-=-
    0.07
    åľ¨é«ĺ
    0.07
    azion
    0.07
     obstante
    0.07
    asiun
    0.07
    =-=-=-=-
    0.07
    amment
    0.06
    BitConverter
    0.06
    æĽľ
    0.06
    Activations Density 0.016%

    No Known Activations