© 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. 40960
    Prev
    Next
    INDEX
    Explanations

    numbers 1, 2, 3, 4, 5, 6

    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
    leigh
    -0.08
    ä¸Ģæĭį
    -0.07
    /con
    -0.07
    ä¸Ģä½ĵæľº
    -0.07
    æŃ£åĢ¼
    -0.07
    ittle
    -0.07
    ipan
    -0.07
    çĥĤ漫
    -0.07
    çĦī
    -0.06
    ëĤĻ
    -0.06
    POSITIVE LOGITS
    ë²Ī
    0.08
    åı·çłģ
    0.07
    åı·
    0.07
    arÃŃa
    0.07
    <number
    0.07
    èĻŁ
    0.07
    åı·ä¸º
    0.07
    è¿Ļ个æķ°åŃĹ
    0.07
    .req
    0.07
    -directory
    0.06
    Activations Density 0.025%

    No Known Activations