© 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. 7196
    Prev
    Next
    INDEX
    Explanations

    units with quantities

    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
    çĦ¶
    -0.07
    sel
    -0.07
    误
    -0.06
    biet
    -0.06
     asympt
    -0.06
    ry
    -0.06
    ------+
    -0.06
    çĦī
    -0.06
    agination
    -0.06
    _Image
    -0.06
    POSITIVE LOGITS
    çļĦè¯Ŀ
    0.07
    å®Ļ
    0.07
    éĢĨè¡Į
    0.07
    åºĩ
    0.07
    ä¸Ĭä¸ĭ
    0.07
    èĥ¶åİŁ
    0.07
    ">&
    0.07
    endr
    0.07
    getConfig
    0.07
    éĢĨåIJij
    0.07
    Activations Density 0.003%

    No Known Activations