© 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. 60739
    Prev
    Next
    INDEX
    Explanations

    options and changes

    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
    æľĢæĸ°æĽ´æĸ°
    -0.08
    åħ¼èģĮ
    -0.07
    æĺłçħ§
    -0.07
    è·Łåįķ
    -0.07
    ä¹Įé¾Ļ
    -0.07
    ragon
    -0.07
    满åłĤ
    -0.07
    colas
    -0.07
     दरà¥į
    -0.06
    æľīåħ¶
    -0.06
    POSITIVE LOGITS
     unlimited
    0.13
    ä¸įéĻIJ
    0.10
    æĹłéĻIJçļĦ
    0.10
     freely
    0.10
    æĹłéĻIJ
    0.10
    ä¸įéĻIJäºİ
    0.10
     Unlimited
    0.09
     infinitely
    0.09
    åħģ许çļĦ
    0.09
     allowed
    0.08
    Activations Density 0.049%

    No Known Activations