© 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. 31187
    Prev
    Next
    INDEX
    Explanations

    possessive name followed by noun

    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
    emann
    -0.08
    ãĥªãĤ¨
    -0.08
    ä¿ĥ
    -0.07
    ستاÙĨÛĮ
    -0.07
    èŁĴ
    -0.07
    AINER
    -0.07
    ĸī
    -0.07
    geh
    -0.07
    izado
    -0.06
    ði
    -0.06
    POSITIVE LOGITS
    orks
    0.08
    ĥ
    0.07
    éĢļåĪĻ
    0.07
    誰ãģ§ãĤĤ
    0.07
    .cn
    0.07
    ought
    0.07
    åı£åijĨ
    0.07
    好人
    0.07
    schau
    0.07
    oria
    0.06
    Activations Density 0.061%

    No Known Activations