© 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. 19372
    Prev
    Next
    INDEX
    Explanations

    between dualisms

    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
    就没
    -0.07
    æ¯Ķäºļ
    -0.07
    onde
    -0.07
    ään
    -0.07
    ondes
    -0.06
    ÑĤоÑĢи
    -0.06
    åĪĺæĻĵ
    -0.06
    åĪĩåIJĪ
    -0.06
    AA
    -0.06
    è·µ
    -0.06
    POSITIVE LOGITS
    ãĢģãĢİ
    0.08
    ®,
    0.07
    ãĢįãĢģãĢĮ
    0.07
    ãĢģ
    0.07
    `,`
    0.07
    ,ep
    0.07
    åIJİèĢħ
    0.07
    agan
    0.07
    et
    0.07
    æĿ
    0.07
    Activations Density 0.150%

    No Known Activations