© 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. 16770
    Prev
    Next
    INDEX
    Explanations

    fractions and math problems

    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
     fore
    -0.07
    !
    -0.07
    utow
    -0.06
    åIJĿåķ¬
    -0.06
     gamm
    -0.06
     bud
    -0.06
    宾
    -0.05
    æĮ¤åĩº
    -0.05
     minus
    -0.05
    adow
    -0.05
    POSITIVE LOGITS
    åĬłæĭ¿å¤§
    0.09
    çķª
    0.08
    timi
    0.08
    .asc
    0.08
    ayat
    0.08
    ÖĦ
    0.08
     consigo
    0.08
     unkompl
    0.08
    кла
    0.08
    emy
    0.08
    Activations Density 0.012%

    No Known Activations