© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29158
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
    Not in Any Lists

    No Comments

    Negative Logits
    rade
    -0.08
    亨
    -0.07
    ipel
    -0.07
    iere
    -0.06
    rip
    -0.06
     Seger
    -0.06
    åĿij
    -0.06
    ords
    -0.06
    èĭ¥éĿŀ
    -0.06
    mun
    -0.06
    POSITIVE LOGITS
    ihal
    0.07
    aving
    0.07
    ุà¸Ķ
    0.07
    ÙĪع
    0.07
    (Code
    0.07
    {'
    0.07
    ä»ĺ诸
    0.07
     gazet
    0.06
     arbitrarily
    0.06
     fool
    0.06
    Activations Density 0.001%

    No Known Activations