© 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. 60703
    Prev
    Next
    INDEX
    Explanations

    judges presiding in court

    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
    ìį¨
    -0.13
    èģĮå®Ī
    -0.10
    enticated
    -0.09
    俱ä¹IJéĥ¨
    -0.09
    çļĦ
    -0.09
    两åѦä¸Ģåģļ
    -0.09
    äºĭåįĬåĬŁåĢį
    -0.08
    ëģĶ
    -0.08
    /she
    -0.08
    éĹ´çĽĺçªģåĩº
    -0.08
    POSITIVE LOGITS
    al
    0.09
    es
    0.09
    è¿ĩçļĦ
    0.08
    е
    0.08
    à¹Į
    0.08
    ing
    0.08
    Ø©
    0.08
    Ùĭ
    0.08
    å®Įæ¯ķåIJİ
    0.08
    ables
    0.07
    Activations Density 0.003%

    No Known Activations