© 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. 34822
    Prev
    Next
    INDEX
    Explanations

    thickness, crops, foods, soft, tube, parts

    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
    raig
    -0.07
    ÐļÑĥпиÑĤÑĮ
    -0.07
    éĩ
    -0.07
    ood
    -0.07
    èIJį
    -0.06
    建ç«ĭåľ¨
    -0.06
    ersh
    -0.06
    æī®æ¼Ķ
    -0.06
    plats
    -0.06
    ius
    -0.06
    POSITIVE LOGITS
     delicate
    0.10
     fragile
    0.10
    èĦĨå¼±çļĦ
    0.09
    å¨ĩ
    0.09
    ãĤ±ãĥ¼ãĥĪ
    0.08
    æĿ¥çĶµåĴ¨è¯¢
    0.08
    aceous
    0.08
     stubborn
    0.08
    èĦĨå¼±
    0.08
    è¿ŀè½½ä¸Ń
    0.08
    Activations Density 0.181%

    No Known Activations