© 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. 42164
    Prev
    Next
    INDEX
    Explanations

    SC can only

    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
    åį´å§ĭç»Ī
    -0.08
    firm
    -0.08
    æ¯Ķ对
    -0.07
    mack
    -0.07
    asl
    -0.07
    éĵ¿
    -0.07
    ÑĢÑĥк
    -0.07
     ÙħÙĤارÙĨØ©
    -0.07
    åį´æĹłæ³ķ
    -0.07
     Giunta
    -0.07
    POSITIVE LOGITS
     Pej
    0.08
    æīĢå±ŀè¡Įä¸ļ
    0.08
    å¾ĹåIJį
    0.08
    sieme
    0.07
    ụng
    0.07
    麻éĽĢ
    0.07
    éĢļ常æĺ¯
    0.06
    éĢĤçĶ¨èĮĥåĽ´
    0.06
     memp
    0.06
    湿äºĨ
    0.06
    Activations Density 0.011%

    No Known Activations