© 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. 20588
    Prev
    Next
    INDEX
    Explanations

    minister or official names

    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
     commenter
    -0.08
    è·Łä¸Ĭ
    -0.08
    Reviewer
    -0.07
    partis
    -0.07
    æĺ¯ä¸Ģå¹´
    -0.07
    çħĮ
    -0.07
    setStatus
    -0.07
    ׼×ķת
    -0.07
    гна
    -0.07
    Scrollbar
    -0.07
    POSITIVE LOGITS
    ä¸Ĭä»»
    0.09
     administration
    0.09
    -appointed
    0.08
     personally
    0.08
     interim
    0.08
    ä»»
    0.08
    åħ¼ä»»
    0.08
     administr
    0.08
     tenure
    0.07
    ä»»æľŁ
    0.07
    Activations Density 0.815%

    No Known Activations