© 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. 43033
    Prev
    Next
    INDEX
    Explanations

    actions followed by specific outcomes or objects

    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
    以任ä½ķ
    -0.07
    ä¸ĭåĨ³å¿ĥ
    -0.07
    ç«Łæĺ¯
    -0.07
    åĵªæĢķæĺ¯
    -0.07
    ETR
    -0.07
     properly
    -0.07
    etz
    -0.07
    åį³å°ĨåĪ°æĿ¥çļĦ
    -0.07
     vaikka
    -0.06
    someone
    -0.06
    POSITIVE LOGITS
    å·¥ä½ľæŶ
    0.10
     often
    0.09
     alot
    0.09
    åıªæľīåľ¨
    0.09
     many
    0.09
    æ´»åĬ¨æŶ
    0.09
    å¾Īå¤ļæŶåĢĻ
    0.09
     ÑĢедко
    0.09
     quite
    0.08
    eldom
    0.08
    Activations Density 0.980%

    No Known Activations