© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42238
    Prev
    Next
    INDEX
    Explanations

    units digit calculation

    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
    æĤł
    -0.06
    bau
    -0.06
    ati
    -0.06
    ç»ķ
    -0.06
    aph
    -0.06
    ä¸įéĻIJ
    -0.06
    ore
    -0.06
    ared
    -0.06
    ear
    -0.06
    é¡·åĪ»
    -0.06
    POSITIVE LOGITS
    éĢĨè¡Į
    0.09
    ä¸ļåĬ¡åıijå±ķ
    0.08
     lej
    0.08
    ä¸ĭä¸Ģç¯ĩ
    0.08
    incar
    0.08
    bacher
    0.08
    vég
    0.08
    ynos
    0.07
    (progress
    0.07
    .mask
    0.07
    Activations Density 0.003%

    No Known Activations