© 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. 32746
    Prev
    Next
    INDEX
    Explanations

    security, data, criteria

    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
    iskus
    -0.08
    æĽ´ä¸įè¦ģ
    -0.07
    ijan
    -0.07
    azit
    -0.07
    å¤ļ头
    -0.07
    ×Ļ׾×Ļ×Ŀ
    -0.07
    ettagli
    -0.07
    ниÑĨÑĥ
    -0.07
    ÑĪкÑĥ
    -0.07
    InputChange
    -0.07
    POSITIVE LOGITS
    ï¸ı
    0.10
    Ø©
    0.08
    sWith
    0.07
    sie
    0.07
    Ñĥн
    0.07
    į
    0.06
    .`
    0.06
    aho
    0.06
    ķ
    0.06
    dorf
    0.06
    Activations Density 0.002%

    No Known Activations