© 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. 32507
    Prev
    Next
    INDEX
    Explanations

    1 or 0

    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
    esen
    -0.09
    æģ©æĸ¯
    -0.08
    æĽ´éķ¿
    -0.08
    è¶Ĭéķ¿
    -0.08
    ĥĿ
    -0.08
    ä½ĵèĤ²è¿IJåĬ¨
    -0.08
    clc
    -0.08
    gados
    -0.08
    ẬN
    -0.08
    åİļçĶŁ
    -0.08
    POSITIVE LOGITS
    åijµ
    0.07
     or
    0.07
    è¸ı
    0.06
     already
    0.06
    us
    0.06
    å·¾
    0.06
    ÏĥÏĮ
    0.06
    æ§
    0.06
    åĩĿç»ĵ
    0.06
    符åIJĪè¦ģæ±Ĥ
    0.06
    Activations Density 0.013%

    No Known Activations