© 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. 44643
    Prev
    Next
    INDEX
    Explanations

    transfer or remove substance

    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
    haar
    -0.07
    涨è·Į
    -0.07
    åĮĸäºĨ
    -0.07
    rome
    -0.07
    ished
    -0.06
    dek
    -0.06
    åĮĸåĴĮ
    -0.06
    arity
    -0.06
    atkan
    -0.06
    ëŀ
    -0.06
    POSITIVE LOGITS
    าà¸ģร
    0.09
    ¶
    0.08
     from
    0.08
    æİł
    0.08
    ãģ£ãģĵ
    0.08
     followed
    0.07
    -from
    0.07
    éģį
    0.07
    éĥ¨ä»½
    0.07
    owler
    0.07
    Activations Density 0.001%

    No Known Activations