© 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. 44527
    Prev
    Next
    INDEX
    Explanations

    ordinary constants and literals

    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
    opter
    -0.09
    eley
    -0.08
    åĪĽä¸ĭ
    -0.08
    èĺĭ
    -0.08
    _reverse
    -0.08
    _rev
    -0.08
    æľĢ主è¦ģçļĦ
    -0.08
    主干éģĵ
    -0.08
    è§Ħ模æľĢ大
    -0.08
    ultipart
    -0.07
    POSITIVE LOGITS
     literal
    0.10
     literally
    0.08
     subscript
    0.08
     literals
    0.07
    åŃĹ
    0.07
     Tre
    0.07
     treated
    0.07
     expression
    0.07
     scalar
    0.07
    literal
    0.07
    Activations Density 0.031%

    No Known Activations