© 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. 60808
    Prev
    Next
    INDEX
    Explanations

    blog posts

    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
    æ¯Ķåݻ年
    -0.06
    ssen
    -0.06
    æ´
    -0.06
    è°Ľ
    -0.06
    ä¸ĸåįļ
    -0.06
    edList
    -0.06
    dorf
    -0.06
    ëIJĺ
    -0.06
    aira
    -0.06
    æĸŃ
    -0.06
    POSITIVE LOGITS
    çĿĢä¸Ģé¢Ĺ
    0.07
    å®īæİĴ好
    0.07
    ç¼ĸæİĴ
    0.07
    éĤ£é¢Ĺ
    0.07
    urr
    0.07
    pery
    0.07
    earing
    0.07
    ynn
    0.07
    -shopping
    0.07
    urre
    0.07
    Activations Density 0.001%

    No Known Activations