© 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. 39317
    Prev
    Next
    INDEX
    Explanations

    the effect

    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
    èĤ¤
    -0.07
    ¿
    -0.07
    onal
    -0.07
    pe
    -0.07
    orer
    -0.06
    alani
    -0.06
    æľī好
    -0.06
    apes
    -0.06
    ĭ
    -0.06
     sake
    -0.06
    POSITIVE LOGITS
    ä¸įæĺ¯åIJĹ
    0.08
    arcer
    0.08
    uchar
    0.08
     Touren
    0.08
    åŃľ
    0.08
    coce
    0.07
    ارب
    0.07
    unto
    0.07
    彿
    0.07
    Scoped
    0.07
    Activations Density 0.358%

    No Known Activations