© 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. 57172
    Prev
    Next
    INDEX
    Explanations

    initializing

    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
    <|box_end|>
    -0.08
    æŃ¤æ¬¾
    -0.08
    omás
    -0.08
    ç»ıå®¡æŁ¥
    -0.08
    iÄĻ
    -0.07
    è¿Ļ款产åĵģ
    -0.07
    onge
    -0.07
    åľ¨ä»ĸ们çļĦ
    -0.07
    çĽ¸å¯¹èĢĮè¨Ģ
    -0.07
    лез
    -0.07
    POSITIVE LOGITS
    lude
    0.07
    ë§ī
    0.06
     dazu
    0.06
    çķ
    0.06
    emente
    0.06
    ä¸ĭä¸Ģ
    0.06
     babe
    0.06
    à¹Ħว
    0.06
    lers
    0.06
    eschi
    0.06
    Activations Density 0.009%

    No Known Activations