© 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. 51225
    Prev
    Next
    INDEX
    Explanations

    metadata separators and list items

    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
    åĪĨç±»ä¸ĵæłı
    -0.08
    æĹłåı¯å¥Īä½ķ
    -0.07
    åıĬåħ¶
    -0.07
    è¿ĺæľī许å¤ļ
    -0.06
    è¿ĺæľīå¾Īå¤ļ
    -0.06
    æľīæĽ´å¤ļçļĦ
    -0.06
    éĤ£åı¥è¯Ŀ
    -0.06
    elmi
    -0.06
     Rev
    -0.06
    eps
    -0.06
    POSITIVE LOGITS
    æīĭåı¯
    0.07
    <|im_start|>
    0.07
    æĺĤ
    0.07
    ãĤģ
    0.07
    semb
    0.07
    ianti
    0.07
     Balik
    0.06
    ·¸
    0.06
    antuan
    0.06
    ainted
    0.06
    Activations Density 0.720%

    No Known Activations