© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62253
    Prev
    Next
    INDEX
    Explanations

    Guardian

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ç¥
    -0.07
    ¬
    -0.06
    odka
    -0.06
    寮
    -0.06
    odal
    -0.06
    olas
    -0.06
    enton
    -0.06
    ischen
    -0.06
    isco
    -0.06
    ân
    -0.06
    POSITIVE LOGITS
    æľŁå¾ħæĤ¨çļĦ
    0.06
    erima
    0.06
    Ỹ
    0.06
    详æĥħ请
    0.06
    rink
    0.06
     ayrıca
    0.06
    erias
    0.06
    æĶ¹çīĪ
    0.06
    Ø®ÙĨ
    0.06
    qed
    0.06
    Activations Density 0.592%

    No Known Activations