© 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. 25640
    Prev
    Next
    INDEX
    Explanations

    two ... phenomena/groups/friends

    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
    argc
    -0.07
    Ñĥк
    -0.07
    ongi
    -0.07
    æĺ¥æĿ¥
    -0.07
    bsub
    -0.07
    elow
    -0.07
    ilk
    -0.07
    nius
    -0.07
     respective
    -0.07
    åĪĨåĪ«æĺ¯
    -0.07
    POSITIVE LOGITS
     notwithstanding
    0.07
    ock
    0.07
    roach
    0.07
     aside
    0.06
    rum
    0.06
    西æŀĹ
    0.06
    opers
    0.06
    è§ģä»ĸ
    0.06
    opsis
    0.06
    Traits
    0.06
    Activations Density 0.005%

    No Known Activations