© 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. 58016
    Prev
    Next
    INDEX
    Explanations

    strength

    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
    иден
    -0.08
    refour
    -0.08
    æĪĸå¤ļ个
    -0.08
    æł·çļĦ
    -0.08
    celli
    -0.08
    ราà¸ĵ
    -0.08
    ÙĬÙĨ
    -0.08
    æīĢéķ¿
    -0.08
    ITY
    -0.08
    culate
    -0.08
    POSITIVE LOGITS
    lessness
    0.10
    less
    0.08
    western
    0.08
    ê¹Ķ
    0.08
    zaam
    0.08
    lessly
    0.07
    OfString
    0.07
    fully
    0.07
    -seeking
    0.07
    kund
    0.07
    Activations Density 0.015%

    No Known Activations