© 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. 2031
    Prev
    Next
    INDEX
    Explanations

    affirmative response followed by punctuation

    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
    èĢĮä»ĸ们
    -0.08
    èĩªçĦ¶ä¹Ł
    -0.07
    ä¸įçł´
    -0.07
    =>'
    -0.07
    ï¼ŁãĢį
    -0.07
    +</
    -0.07
    à¸ĺรรมà¸Ĭาà¸ķิà¹ģละ
    -0.07
    åĪ°åºķæĺ¯
    -0.07
    究竣æĺ¯
    -0.07
    ocken
    -0.07
    POSITIVE LOGITS
    !
    0.08
    à¸Ħรัà¸ļ
    0.07
    åĽłä¸ºåľ¨
    0.07
    ainkan
    0.06
    人身
    0.06
    !,
    0.06
     Ingy
    0.06
    æ°Ķé¦ģ
    0.06
     à¸Ħรัà¸ļ
    0.06
    inki
    0.06
    Activations Density 0.059%

    No Known Activations