© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 49938
    Prev
    Next
    INDEX
    Explanations

    popup followed by parenthesis

    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
    æĩĤ
    -0.08
    -generic
    -0.07
     Poz
    -0.07
    åĪĿæŃ¥
    -0.07
    aus
    -0.07
    ɵ
    -0.07
    elog
    -0.07
    pos
    -0.06
    裸
    -0.06
    ongyang
    -0.06
    POSITIVE LOGITS
    another
    0.09
     another
    0.08
     nữa
    0.08
    avana
    0.08
     dÆ°
    0.07
    åıĪæĺ¯ä¸Ģ
    0.07
    继ç»Ń
    0.07
    çļĦåı¦ä¸Ģ
    0.07
    éĺħ读éĩı
    0.07
    à¸Ńีà¸ģ
    0.07
    Activations Density 0.013%

    No Known Activations