© 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. 43431
    Prev
    Next
    INDEX
    Explanations

    based on results and findings

    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
    éĶ¦æ¶Ľ
    -0.09
    åĪĪ
    -0.08
    odor
    -0.08
    apore
    -0.08
    ä¸įçĦ¶
    -0.08
    impin
    -0.08
     <<-
    -0.08
    çļĦ好æĪIJ绩
    -0.08
    æ¯ķç«Ł
    -0.08
    ugend
    -0.08
    POSITIVE LOGITS
    并ç»ĵåIJĪ
    0.07
     suggests
    0.06
     and
    0.06
    ,
    0.06
    æľīæīĢæĢĿ
    0.06
    ä½łå°±èĥ½
    0.06
    åĵªä¸Ģç§į
    0.06
    opi
    0.06
    ä½łæĢİä¹Ī
    0.06
     conclude
    0.06
    Activations Density 0.010%

    No Known Activations