© 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. 63858
    Prev
    Next
    INDEX
    Explanations

    meeting requirements or criteria

    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
    ä¸ĭåIJĮ
    -0.08
    ellone
    -0.08
    æĽ´å¤ļåĨħ容
    -0.08
    ajer
    -0.07
     triá»ĩt
    -0.07
    صرÙĬ
    -0.07
    ureka
    -0.07
    erman
    -0.07
    å¬Ľ
    -0.07
    tschaft
    -0.07
    POSITIVE LOGITS
    æĹ¢å®ļ
    0.09
    è§Ħå®ļçļĦ
    0.09
    à¹Ģà¸ģà¸ĵà¸ijà¹Į
    0.09
     muster
    0.09
    设计è¦ģæ±Ĥ
    0.09
    è¦ģæ±ĤçļĦ
    0.08
    æĪĸæľª
    0.08
    _req
    0.08
    è§Ħå®ļ
    0.08
     requirements
    0.07
    Activations Density 0.138%

    No Known Activations