© 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. 4057
    Prev
    Next
    INDEX
    Explanations

    trial or probe

    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
    NESS
    -0.08
    ä¼ĹæīĢåij¨çŁ¥
    -0.08
    -than
    -0.08
    ä½Ĩä¸įéĻIJäºİ
    -0.08
    ials
    -0.08
    ftime
    -0.08
    illary
    -0.08
    encies
    -0.07
    ÑģÑĤÑĢ
    -0.07
    ypress
    -0.07
    POSITIVE LOGITS
    ر
    0.11
    zelfde
    0.09
    áŁĭ
    0.09
    erweise
    0.09
    AndUpdate
    0.08
    äºĨ
    0.08
    à§ĩ
    0.08
    StringLength
    0.07
    enberg
    0.07
    گاÙĩÛĮ
    0.07
    Activations Density 0.096%

    No Known Activations