© 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. 27761
    Prev
    Next
    INDEX
    Explanations

    calculating function outputs

    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
    ä½ļåIJį
    -0.08
    clip
    -0.07
    umer
    -0.07
    åIJijèį£
    -0.07
    åļİ
    -0.07
    ï¸İ
    -0.07
    åħĭç¦ı
    -0.07
    å¦Ĭ
    -0.07
    èĽĨ
    -0.07
    úm
    -0.07
    POSITIVE LOGITS
    åIJĪ家
    0.07
    adata
    0.07
    ugh
    0.07
    дова
    0.06
    anson
    0.06
    nesia
    0.06
    achers
    0.06
    živ
    0.06
    ugar
    0.06
    tora
    0.06
    Activations Density 0.006%

    No Known Activations