© 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. 40664
    Prev
    Next
    INDEX
    Explanations

    inside, middle, or interior regions

    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
    char
    -0.07
    æĨ²
    -0.07
    è¯Ĺç¯ĩ
    -0.07
    éĤ£è¾¹çļĦ
    -0.07
    ãĥĻãĥ¼ãĤ¹
    -0.07
    åİŁçīĪ
    -0.07
    ahlen
    -0.06
    иÑģÑĤо
    -0.06
    å·®å¼ĤæĢ§
    -0.06
    eer
    -0.06
    POSITIVE LOGITS
    ä¸ŃéĹ´
    0.10
     intermediate
    0.09
    floating
    0.09
     interior
    0.09
    eluk
    0.09
    ä¸Ńéĥ¨
    0.08
     interiores
    0.08
     mid
    0.08
    ä¸ŃéĹ´çļĦ
    0.08
     ÙħÙĨتصÙģ
    0.08
    Activations Density 0.065%

    No Known Activations