© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 890
    Prev
    Next
    INDEX
    Explanations

    or something

    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
    没æľīä»»ä½ķ
    -0.07
    çIJĨä¼ļ
    -0.07
    çIJĨæīĢå½ĵçĦ¶
    -0.07
    ä»»ä½ķåħ¶ä»ĸ
    -0.07
    YN
    -0.07
    çªģ
    -0.07
    æŶ令
    -0.06
    olda
    -0.06
     Ass
    -0.06
    Ass
    -0.06
    POSITIVE LOGITS
    æĢ»ä¹ĭ
    0.08
    大æĦı
    0.08
    citation
    0.08
    depending
    0.07
    åħ·ä½ĵ
    0.07
    _BOUNDS
    0.07
    æĪijåIJ¬
    0.07
     [*
    0.07
    /details
    0.07
    òng
    0.07
    Activations Density 0.015%

    No Known Activations