© 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. 2027
    Prev
    Next
    INDEX
    Explanations

    i look forward to

    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
    è¯ł
    -0.07
    å°±æĺ¯äºĨ
    -0.07
     suy
    -0.07
    æĪijåħĪ
    -0.07
    强è¡Į
    -0.07
    æľīåı¯èĥ½æĺ¯
    -0.07
    ä¹Łä¸įå¿ħ
    -0.07
    åı¯èĥ½å°±æĺ¯
    -0.07
    igo
    -0.07
    æĪĸ许æĺ¯
    -0.07
    POSITIVE LOGITS
    并å¸ĮæľĽ
    0.12
    è¦ģæ±ĤåIJĦ
    0.12
    à¸ķà¹īà¸Ńà¸ĩà¸ģาร
    0.11
     want
    0.11
    éĥ½å¸ĮæľĽ
    0.11
    æ¸´æľĽ
    0.11
    å¸ĮæľĽéĢļè¿ĩ
    0.10
     prefers
    0.10
     prefer
    0.10
    å¸ĮæľĽåľ¨
    0.10
    Activations Density 0.473%

    No Known Activations