© 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. 44546
    Prev
    Next
    INDEX
    Explanations

    words starting with f

    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
    ê¹IJ
    -0.10
    oo
    -0.08
    umber
    -0.08
    arily
    -0.08
    eration
    -0.08
    fass
    -0.08
    樣çļĦ
    -0.08
    aries
    -0.07
    arity
    -0.07
    ary
    -0.07
    POSITIVE LOGITS
    ़
    0.17
    razier
    0.14
    letcher
    0.14
    alcon
    0.12
    amiliar
    0.12
    avourites
    0.12
    erguson
    0.12
    ergus
    0.12
    AMILY
    0.11
    UTURE
    0.11
    Activations Density 0.966%

    No Known Activations