© 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. 4841
    Prev
    Next
    INDEX
    Explanations

    code blocks

    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
    ician
    -0.09
    ิà¸Ķ
    -0.07
    icing
    -0.07
    ê¹IJ
    -0.07
    heits
    -0.07
    _allocated
    -0.07
    ichtigung
    -0.07
    ljiv
    -0.07
    ücken
    -0.07
    eenth
    -0.07
    POSITIVE LOGITS
    ÑĤÑĢе
    0.08
    麽
    0.08
    &(
    0.07
    ÙĪرÙĪ
    0.07
    ARSE
    0.07
    mur
    0.07
    kal
    0.06
    zell
    0.06
    ollen
    0.06
    gan
    0.06
    Activations Density 0.114%

    No Known Activations