© 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. 4731
    Prev
    Next
    INDEX
    Explanations

    list indexing, loop counters

    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
     neither
    -0.06
    ono
    -0.06
    çī¹çĤ¹æĺ¯
    -0.06
    ativa
    -0.06
    ä¸įæĺ¯å¾Ī好
    -0.06
    athon
    -0.06
     moot
    -0.06
     violations
    -0.06
    ativas
    -0.06
    br
    -0.06
    POSITIVE LOGITS
    лежа
    0.08
    +offset
    0.08
    chwitz
    0.08
    lei
    0.08
    ارÙĬÙĨ
    0.08
    edic
    0.08
     Olah
    0.08
    à¤Ĺà¥ĩ
    0.08
     besti
    0.07
    esak
    0.07
    Activations Density 0.007%

    No Known Activations