© 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. 44644
    Prev
    Next
    INDEX
    Explanations

    generated by

    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
    jenigen
    -0.11
    tures
    -0.11
    اÙĭ
    -0.10
    åħ¥å¾®
    -0.10
    iac
    -0.10
    ezza
    -0.10
    antly
    -0.09
    nowled
    -0.09
    eam
    -0.09
    erior
    -0.09
    POSITIVE LOGITS
    nt
    0.12
    /is
    0.11
    es
    0.11
    à§ĩ
    0.09
    en
    0.08
    i
    0.08
    bsites
    0.08
    æĺ¯
    0.08
    ãĤī
    0.08
    å¥Īä½ķ
    0.07
    Activations Density 0.538%

    No Known Activations