© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 52061
    Prev
    Next
    INDEX
    Explanations

    surface of membrane, body, face

    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
    Negative Logits
    adang
    -0.08
    enang
    -0.08
    ibo
    -0.07
    пÑĢоÑĩем
    -0.07
    encial
    -0.07
     кÑģÑĤаÑĤи
    -0.07
    人们对
    -0.07
    人们çĶŁæ´»
    -0.07
    æĪĸèĢħæľī
    -0.07
     btw
    -0.07
    POSITIVE LOGITS
    æķħèĢĮ
    0.07
    ropp
    0.07
    ä¸įçķĻ
    0.06
    以èĩ´
    0.06
    #$
    0.06
    elig
    0.06
    ä»İèĢĮ
    0.06
    ×¥
    0.06
     Trinh
    0.06
    chi
    0.06
    Activations Density 0.032%

    No Known Activations