© 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. 3222
    Prev
    Next
    INDEX
    Explanations

    implicit, unintentionally, logical

    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
    åIJįåī¯åħ¶å®ŀçļĦ
    -0.08
    siÄĻ
    -0.08
    ç´¢æĢ§
    -0.08
    arty
    -0.08
    eting
    -0.07
    leine
    -0.07
    =device
    -0.07
    ä»ħä»ħæĺ¯
    -0.07
    顾åIJįæĢĿä¹ī
    -0.07
    该åIJį
    -0.07
    POSITIVE LOGITS
    ëĤĺë§Ī
    0.12
    ãģªãģĮãĤī
    0.10
    Implicit
    0.10
    implicit
    0.09
     implicit
    0.09
    éļIJåIJ«
    0.09
    æ½ľ
    0.09
     Implicit
    0.09
    æĪĸ缴æİ¥
    0.09
    æļĹ
    0.09
    Activations Density 0.068%

    No Known Activations