© 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. 37662
    Prev
    Next
    INDEX
    Explanations

    citation references or academic context

    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
    Negative Logits
    ož
    -0.09
    бÑĢ
    -0.07
    ugin
    -0.07
    _boxes
    -0.07
     pró
    -0.07
    .wrap
    -0.07
    BR
    -0.07
    æı´
    -0.07
    жаÑĤ
    -0.06
    å¹¢
    -0.06
    POSITIVE LOGITS
    ä¸Ģåĭº
    0.08
    çı
    0.08
    nder
    0.07
    uzz
    0.07
    认è¯ĨçļĦ
    0.07
    ä¹ĭåīij
    0.07
     Robbins
    0.07
    _MPI
    0.07
    åħ¨ä½ĵæķĻå¸Ī
    0.07
    שר×IJ׾
    0.07
    Activations Density 0.010%

    No Known Activations