© 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. 20497
    Prev
    Next
    INDEX
    Explanations

    urge to move

    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
    elaar
    -0.08
    å¥ķ
    -0.08
    å¼Ĥ
    -0.08
    Ñĥди
    -0.08
    éĶ¦æ¶Ľ
    -0.08
    éĹŃéŨ
    -0.07
    èĪ
    -0.07
    ô
    -0.07
    è´¯
    -0.07
    ä¸įè¯Ĩ
    -0.07
    POSITIVE LOGITS
    ðĿ
    0.07
    ¹
    0.07
    ลุ
    0.07
    ï¸İ
    0.06
    çIJĥ迷们
    0.06
    agged
    0.06
     ↵↵
    0.06
    ä»Ģä¹ĪçļĦ
    0.06
    izzard
    0.06
     meis
    0.06
    Activations Density 0.085%

    No Known Activations