© 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. 47738
    Prev
    Next
    INDEX
    Explanations

    unit of measure

    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
    åħĪçĶ¨
    -0.08
     radial
    -0.07
    -hard
    -0.07
    ãĤľ
    -0.07
     retention
    -0.07
    两éĿ¢
    -0.07
     bestaan
    -0.07
    æµĬ
    -0.07
    ÑĢеменно
    -0.07
    \s
    -0.07
    POSITIVE LOGITS
    ctp
    0.08
    åįĺä½į
    0.08
    为åįķä½į
    0.08
     indiv
    0.08
    对æķ´ä¸ª
    0.08
    åįķä½į
    0.08
     unit
    0.07
    unit
    0.07
    /single
    0.07
     sto
    0.07
    Activations Density 0.007%

    No Known Activations