© 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. 52130
    Prev
    Next
    INDEX
    Explanations

    directory and build paths

    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
     hypo
    -0.07
    holm
    -0.06
    éĽĨåIJĪ
    -0.06
    ائÙħ
    -0.06
    -dev
    -0.06
    æĦıåľ¨
    -0.06
    held
    -0.06
     claimed
    -0.06
    æŀĦæĢĿ
    -0.06
    attoo
    -0.06
    POSITIVE LOGITS
     bim
    0.09
    icata
    0.08
    ptest
    0.08
    าà¸Ħ
    0.08
    ç»ĵæŀľä¸º
    0.08
    ×ŀצ
    0.08
    TextNode
    0.08
    -bin
    0.08
    бина
    0.08
     kant
    0.08
    Activations Density 0.041%

    No Known Activations