© 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. 55778
    Prev
    Next
    INDEX
    Explanations

    programming and special characters

    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
    åŃ¦ä»¥èĩ´
    -0.07
    æŶåı¯ä»¥
    -0.07
    æĹ¶è¢«
    -0.07
    holt
    -0.06
    weisen
    -0.06
    ãĥĩãĤ£ãĤª
    -0.06
    åľ°çĥŃ
    -0.06
    æīĢè§ģ
    -0.06
    æĹ¶å°±
    -0.06
    åIJİ被
    -0.06
    POSITIVE LOGITS
    iant
    0.09
    iat
    0.08
    িয়
    0.08
    indu
    0.07
    imb
    0.07
    rzy
    0.07
    bling
    0.07
    iatr
    0.07
    /global
    0.07
    amar
    0.07
    Activations Density 0.071%

    No Known Activations