© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7113
    Prev
    Next
    INDEX
    Explanations

    wedge-shaped, component, lengths

    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
    Negative Logits
    èĩªæĿ¥
    -0.08
    åĽĽéĢļ
    -0.08
    lington
    -0.07
    åIJĦè·¯
    -0.07
    ussian
    -0.07
     Ons
    -0.07
    è¿ĺæĺ¯ä¸Ģ个
    -0.06
    大åħ´
    -0.06
    xin
    -0.06
    fid
    -0.06
    POSITIVE LOGITS
    _accessor
    0.08
     lengths
    0.08
    è¾¹çļĦ
    0.07
    _sizes
    0.07
    -Length
    0.07
    汤åĮĻ
    0.07
    hipster
    0.07
    éģµ
    0.06
    icine
    0.06
    _lengths
    0.06
    Activations Density 0.001%

    No Known Activations