© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 57065
    Prev
    Next
    INDEX
    Explanations

    list items or code blocks

    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
    ijken
    -0.06
    ustin
    -0.06
    ç¾İåĽ¾
    -0.06
    uren
    -0.06
    åı¸é©¬
    -0.06
    æ¯ıåĪ°
    -0.06
    \\
    -0.06
    eu
    -0.06
    /{
    -0.06
    ä¸įè¿ĺ
    -0.06
    POSITIVE LOGITS
    åĭĩå¾Ģ缴åīį
    0.09
    åħ¢åħ¢ä¸ļä¸ļ
    0.09
    âĢ¦]
    0.09
    ä¸įåı¯æĢĿè®®
    0.08
    äºĭåįĬåĬŁåĢį
    0.08
    ðŁĺĢ
    0.08
    åĭ¤åĭ¤æģ³æģ³
    0.08
    زة
    0.08
    ç½²
    0.07
    åºıåĪĹ
    0.07
    Activations Density 0.031%

    No Known Activations