© 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. 18511
    Prev
    Next
    INDEX
    Explanations

    now/however followed by intent

    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
    boten
    -0.09
    Ñij
    -0.08
    emuk
    -0.08
    enance
    -0.08
    æīĢ以她
    -0.08
    çļĦè¿ĺæľī
    -0.08
    ancen
    -0.07
    æīĢä»¥ä½ł
    -0.07
    æĽ´ä½ķåĨµ
    -0.07
    riet
    -0.07
    POSITIVE LOGITS
    顾åIJįæĢĿä¹ī
    0.08
    æĺ¯æĥ³
    0.07
    cg
    0.06
    ä¼ĹæīĢåij¨çŁ¥
    0.06
    ora
    0.06
    оÑĢа
    0.06
    ¯
    0.06
    yra
    0.06
    sth
    0.06
    åīįæľŁçļĦ
    0.06
    Activations Density 0.021%

    No Known Activations