© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17739
    Prev
    Next
    INDEX
    Explanations

    nitroso compounds or nitrite

    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
    ä¼Łä¸ļ
    -0.08
    æ·¼
    -0.07
    rane
    -0.07
    æľīå¿ĥ人
    -0.07
    ertools
    -0.07
    olph
    -0.07
    ergus
    -0.07
    izou
    -0.07
    ?key
    -0.07
    agna
    -0.07
    POSITIVE LOGITS
    okes
    0.07
    alam
    0.07
    æĸĩ
    0.07
    halb
    0.06
    scr
    0.06
    ed
    0.06
    ansi
    0.06
    榻
    0.06
    æĸĩå±±
    0.06
    ux
    0.06
    Activations Density 0.006%

    No Known Activations