© 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. 49589
    Prev
    Next
    INDEX
    Explanations

    magic, magical

    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
    .Builder
    -0.08
    GLOBALS
    -0.08
    upro
    -0.07
    å®īåħ¨ç¬¬ä¸Ģ
    -0.07
    ÑĢин
    -0.07
    缮å®ī
    -0.07
    æŃ£è½¨
    -0.07
    erval
    -0.07
    ož
    -0.07
    olutely
    -0.07
    POSITIVE LOGITS
    èİ«æµĭ
    0.11
     magic
    0.09
    æľ¯
    0.09
    å¸ĪçļĦ
    0.09
    magic
    0.09
    éŃĶæ³ķ
    0.09
    ç¥ŀå¥ĩçļĦ
    0.08
    ä¸İçİ°å®ŀ
    0.08
    ç¥ŀå¥ĩ
    0.08
    èĪ¬åľ°
    0.08
    Activations Density 0.144%

    No Known Activations