© 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. 47380
    Prev
    Next
    INDEX
    Explanations

    Ricky started

    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
     soit
    -0.08
     among
    -0.06
    ç´«èĸĩ
    -0.06
    among
    -0.06
    anz
    -0.06
     amongst
    -0.06
    人äºĭ
    -0.06
    ussy
    -0.06
    毫
    -0.06
    ä¸Ģæīĭ
    -0.05
    POSITIVE LOGITS
    mdir
    0.09
     nhau
    0.08
    ä¹ĭå¤Ħåľ¨äºİ
    0.08
    ç»Ļ人çļĦ
    0.08
    ç®ĹäºĨ
    0.08
    cling
    0.08
    amana
    0.08
    ="__
    0.08
    å¼ķ以为
    0.08
    tures
    0.07
    Activations Density 0.002%

    No Known Activations