© 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. 56351
    Prev
    Next
    INDEX
    Explanations

    data formatting and types

    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
    çĬ¹
    -0.07
    гово
    -0.07
    match
    -0.06
     fili
    -0.06
    lessness
    -0.06
    ilver
    -0.06
    ocache
    -0.06
    èĿ¶
    -0.06
    consts
    -0.06
    AZY
    -0.06
    POSITIVE LOGITS
    ä¸įéĻIJ
    0.07
    eer
    0.07
    æĿ¥éĻ¢
    0.07
    å¼ģ
    0.07
    ibase
    0.07
    raw
    0.07
    ä¸įåĪĨ
    0.06
    æĹłæīĢè°ĵ
    0.06
    建议åĴĮ
    0.06
    æŀĦæĪIJçĬ¯ç½ªçļĦ
    0.06
    Activations Density 0.016%

    No Known Activations