© 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. 7136
    Prev
    Next
    INDEX
    Explanations

    list items or code comments

    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
    触
    -0.08
    çļĦä¸Ĭ
    -0.06
    åIJĪ
    -0.06
    fulness
    -0.06
    uhn
    -0.06
    —
    -0.06
    (
    -0.06
    eness
    -0.06
    zog
    -0.06
    PI
    -0.06
    POSITIVE LOGITS
    [âĢ¦
    0.10
    ÏģÏĩ
    0.09
    :''
    0.08
    Ñĩал
    0.08
    reator
    0.07
    wap
    0.07
    ASK
    0.07
    elok
    0.07
    reens
    0.07
    osg
    0.07
    Activations Density 0.008%

    No Known Activations