© 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. 22352
    Prev
    Next
    INDEX
    Explanations

    peak, line, spot, band, fringe

    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
    Õ¡Õ¯Õ¡Õ¶
    -0.09
    ä¹ĭæĺŁ
    -0.09
    essant
    -0.08
    ä¸į详
    -0.08
    _DEFINED
    -0.08
    èĩ´ä½¿
    -0.08
    åIJĽå®ī
    -0.08
    ä¸įåıĬå¾ħ
    -0.08
    ereal
    -0.08
    (EXPR
    -0.08
    POSITIVE LOGITS
    ç¿
    0.08
     representing
    0.08
    代表
    0.07
    强度
    0.07
     sizes
    0.06
    bel
    0.06
    eri
    0.06
    çļĦåĩºçİ°
    0.06
    群
    0.06
     size
    0.06
    Activations Density 0.029%

    No Known Activations