© 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. 4623
    Prev
    Next
    INDEX
    Explanations

    results showed that

    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
    urkan
    -0.06
    ç¨½æł¸
    -0.06
    oby
    -0.06
    ç¼ħ
    -0.06
     ...,
    -0.06
    æĹłåıį
    -0.06
    çĵ®
    -0.06
    UP
    -0.06
    èĢ
    -0.06
    è¿Ļæł·çļĦä¸Ģ个
    -0.06
    POSITIVE LOGITS
    è¦ģæ±Ĥåľ¨
    0.08
    æĵįä½ľæĸ¹æ³ķ
    0.07
    åĩłä¸ªäºº
    0.07
    è§ģ表
    0.07
    åıĪåı«
    0.07
    çľĭçĤ¹
    0.07
    olars
    0.07
    ezo
    0.07
    åĩłç§į
    0.07
    æľī以ä¸ĭ
    0.07
    Activations Density 0.006%

    No Known Activations