© 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. 59109
    Prev
    Next
    INDEX
    Explanations

    simplest or trivial cases

    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
    icense
    -0.08
    åİ»å¤Ħ
    -0.07
    Ñħла
    -0.07
    _ASSUME
    -0.07
    amber
    -0.07
    å¡ĺéķĩ
    -0.07
    ÑĦиÑĨи
    -0.07
    ÑĦÑĦ
    -0.07
    odar
    -0.07
    æĿ¥ä¹ĭä¸įæĺĵ
    -0.07
    POSITIVE LOGITS
     trivial
    0.08
    æľĢç®ĢåįķçļĦ
    0.08
    /default
    0.07
    åĪĿå§ĭ
    0.07
     simplest
    0.07
    æľĢç®Ģåįķ
    0.07
    lež
    0.07
    æľĢåŁºæľ¬
    0.07
    æľĢä½İçļĦ
    0.07
    ä¸įåĪĨ
    0.06
    Activations Density 0.308%

    No Known Activations