© 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. 57362
    Prev
    Next
    INDEX
    Explanations

    digit of a number

    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
    åķ¡
    -0.09
    anford
    -0.08
    itto
    -0.08
    pill
    -0.08
    ulte
    -0.08
    еÑģÑĤв
    -0.08
    ItemAt
    -0.08
    ÙĨدر
    -0.08
    ä¸İä½ľçĶ¨
    -0.08
    .Sp
    -0.08
    POSITIVE LOGITS
    èĬĴ
    0.07
    ena
    0.06
    aise
    0.06
    ìĿµ
    0.06
    ade
    0.06
    eka
    0.06
    éľĢè¦ģä¸Ģ个
    0.06
    Decimal
    0.06
    ths
    0.06
     grid
    0.06
    Activations Density 0.012%

    No Known Activations