© 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. 16162
    Prev
    Next
    INDEX
    Explanations

    similar questions or problems

    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
    aad
    -0.09
    yel
    -0.09
    ungg
    -0.08
    erat
    -0.08
     psyche
    -0.08
    æĺ¯éĤ£
    -0.08
    esas
    -0.07
    edReader
    -0.07
    azz
    -0.07
    ä¸½å¨ľ
    -0.07
    POSITIVE LOGITS
    äºİä¸Ģ
    0.09
    äºİæѤ
    0.09
     halnya
    0.09
    -minded
    0.08
    ä¹İ
    0.08
    ç¨ĭ度çļĦ
    0.08
    à¹Ģà¸Ķียวà¸ģัà¸Ļ
    0.07
    -ci
    0.07
    ness
    0.07
    rett
    0.07
    Activations Density 0.018%

    No Known Activations