© 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. 682
    Prev
    Next
    INDEX
    Explanations

    adding extra, recently up, conducted to

    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
    à¸ĺุ
    -0.07
    ák
    -0.07
    oi
    -0.07
    etos
    -0.07
    erring
    -0.07
    kamp
    -0.06
    ãĥ¬ãĥ¼ãĤ·ãĥ§ãĥ³
    -0.06
    onus
    -0.06
    象
    -0.06
    æ°ĵ
    -0.06
    POSITIVE LOGITS
    沫
    0.08
    çĦ¶çļĦ
    0.07
    çĦ¶
    0.07
    indert
    0.07
    çĦ¶èĢĮ
    0.07
    æİī
    0.07
    ç¨ĭ
    0.07
    éķľ
    0.07
    é¦ĸ度
    0.07
    tier
    0.07
    Activations Density 0.187%

    No Known Activations