© 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. 17188
    Prev
    Next
    INDEX
    Explanations

    proper names of characters

    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
     chic
    -0.07
    èĪ¬çļĦ
    -0.06
    æĥĭæĥľ
    -0.06
    ÑĢÑģ
    -0.06
     combining
    -0.05
    ¤
    -0.05
    è¶ħä½İ
    -0.05
    ai
    -0.05
    ä¸įä¿Ĺ
    -0.05
    该å¸Ĥ
    -0.05
    POSITIVE LOGITS
    mania
    0.09
    hod
    0.08
    ért
    0.08
    .tpl
    0.08
    èĥŀ
    0.08
    à¹Ģà¸Ńà¸ĩ
    0.08
     returned
    0.08
    amanca
    0.08
    è¿ĶåĽŀ
    0.08
    以为çĦ¶
    0.07
    Activations Density 0.048%

    No Known Activations