© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 57212
    Prev
    Next
    INDEX
    Explanations

    closing code/syntax

    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
    èµĸ
    -0.07
    ième
    -0.07
    ssql
    -0.07
    鲸
    -0.07
    opin
    -0.07
    ugo
    -0.07
    er
    -0.07
    noinspection
    -0.06
    毫ä¸į
    -0.06
    ä½Ĩä¸įéĻIJäºİ
    -0.06
    POSITIVE LOGITS
    OMA
    0.08
     [âĢ¦]
    0.07
    ongan
    0.07
    å¹´å¹´
    0.07
     [âĢ¦
    0.07
    unia
    0.06
    برت
    0.06
    Ñĩи
    0.06
    åı«
    0.06
    доми
    0.06
    Activations Density 0.195%

    No Known Activations