© 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. 10779
    Prev
    Next
    INDEX
    Explanations

    compositional inverse, ViewController

    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
    loed
    -0.07
    ajs
    -0.07
    ih
    -0.07
    alsy
    -0.06
    hide
    -0.06
     Sett
    -0.06
    สà¹Ģà¸ķà¸Ńรà¹Į
    -0.06
    ায়
    -0.06
    sett
    -0.06
    å¯
    -0.06
    POSITIVE LOGITS
    å¦Ĥæŀľåı¯ä»¥
    0.12
    èĭ¥æľī
    0.10
    å¿ħé¡»æľī
    0.10
    åīįæıIJæĺ¯
    0.10
     Danger
    0.09
    åı¯è¡ĮæĢ§
    0.09
    å¿ħé¡»è¦ģæľī
    0.09
    å¿ħé¡»åħ·å¤ĩ
    0.09
    åı¯èĥ½åŃĺåľ¨
    0.09
    elig
    0.09
    Activations Density 0.054%

    No Known Activations