© 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. 4819
    Prev
    Next
    INDEX
    Explanations

    numbers, country, or code sections

    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
    ÙĪÙħاÙĨ
    -0.07
    ç¯ĩäºĮ
    -0.07
    ritt
    -0.07
    jeros
    -0.07
    agian
    -0.07
     Soi
    -0.07
    isa
    -0.07
    ój
    -0.07
    è¿ĺè´·
    -0.06
     Reit
    -0.06
    POSITIVE LOGITS
    uated
    0.07
    RLF
    0.07
    powered
    0.07
    اØŃت
    0.07
    chá
    0.07
    há
    0.07
    å¾·éŁ³
    0.07
    ī¬
    0.06
    oug
    0.06
    se
    0.06
    Activations Density 0.084%

    No Known Activations