© 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. 51321
    Prev
    Next
    INDEX
    Explanations

    operational, limited, or higher

    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
    plet
    -0.07
    è¶Ł
    -0.07
    plets
    -0.07
    è¡¥
    -0.06
    以德
    -0.06
     Kou
    -0.06
    家常
    -0.06
    éĴ§
    -0.06
    æľīéģĵ
    -0.06
    å¾Īå¤ļ次
    -0.06
    POSITIVE LOGITS
    å°±ä¸įåĨį
    0.14
    ä¹Łä¸įåĨį
    0.13
    ä¸įåĨį
    0.13
    åĨįä¹Łä¸į
    0.12
     désormais
    0.12
     anymore
    0.12
    ä¸įåĨįæľī
    0.12
    ä¸įåĨįæĺ¯
    0.12
     ÏĢλÎŃον
    0.12
     geworden
    0.11
    Activations Density 0.632%

    No Known Activations