© 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. 56354
    Prev
    Next
    INDEX
    Explanations

    scheme, construction, procedure

    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
    izzi
    -0.10
    ç·ıåIJĪ
    -0.07
    å®ĥæīĢ
    -0.07
    compile
    -0.07
    emean
    -0.07
    ä¼ģä¸ļ管çIJĨåĴ¨è¯¢
    -0.07
    åĩĨ确度
    -0.07
     scope
    -0.06
    issy
    -0.06
    Joined
    -0.06
    POSITIVE LOGITS
    æĸ¹æ¡Ī
    0.10
    æĸ¹æ¡ĪçļĦ
    0.09
     constructions
    0.09
     constructing
    0.09
    çļĦæĸ¹æ¡Ī
    0.09
     devised
    0.09
     construction
    0.08
    æĸ¹æ¡Ī设计
    0.08
     ingenious
    0.08
     scheme
    0.08
    Activations Density 0.009%

    No Known Activations