© 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. 18212
    Prev
    Next
    INDEX
    Explanations

    physical, fragility, puzzle, detention, stalk, bodily

    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
    缸åħ³æݨèįIJ
    -0.10
    menti
    -0.10
    esm
    -0.09
    ÑģÑģоÑĢа
    -0.09
    zana
    -0.09
    ÑģÑĤили
    -0.09
    bbie
    -0.09
    åĬłåħ¥ä¹¦çŃ¾
    -0.09
    俱ä¹IJéĥ¨
    -0.09
    usercontent
    -0.09
    POSITIVE LOGITS
    /
    0.10
    ãĢģ
    0.09
    ､
    0.08
    âĢIJ
    0.08
    âĢij
    0.08
    -
    0.07
    æĪĸ
    0.07
     and
    0.07
    ,
    0.06
    ÂŃ
    0.06
    Activations Density 0.143%

    No Known Activations