© 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. 24770
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and specific nouns

    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
    ope
    -0.06
    ate
    -0.06
    arn
    -0.06
    ẹn
    -0.06
    æĨ¨
    -0.06
    座
    -0.06
    èķĬ
    -0.06
    rita
    -0.06
    agen
    -0.06
    _recovery
    -0.06
    POSITIVE LOGITS
    oins
    0.07
    awang
    0.07
    ssia
    0.07
     ConnectionState
    0.07
    éĵ¶è¡Įè´¦æĪ·
    0.07
    athi
    0.07
    queta
    0.07
    prs
    0.07
    æīĵä¸ĭåĿļå®ŀçļĦåŁºç¡Ģ
    0.07
    mor
    0.07
    Activations Density 0.002%

    No Known Activations