© 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. 1108
    Prev
    Next
    INDEX
    Explanations

    always followed by a verb

    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
    çļĦæīĢæľī
    -0.10
    ç§įç§į
    -0.09
    ught
    -0.09
    ä¸Ģ缴ä¿ĿæĮģ
    -0.09
    å®Įåħ¨åı¯ä»¥
    -0.08
    ppure
    -0.08
    ÑģеÑĤ
    -0.08
    缴æİ¥å°Ĩ
    -0.08
    er
    -0.08
     ìĿ¼ìłĪ
    -0.08
    POSITIVE LOGITS
    ness
    0.10
     تÙĤرÙĬب
    0.08
    ìĸ´ëĤľ
    0.08
    igator
    0.08
    è®°å¾Ĺ
    0.08
    izr
    0.08
     Äijặn
    0.08
    cky
    0.07
    nya
    0.07
    thing
    0.07
    Activations Density 0.027%

    No Known Activations