© 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. 34738
    Prev
    Next
    INDEX
    Explanations

    positive test results

    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
    stuff
    -0.08
     stuff
    -0.07
    gid
    -0.07
    æĸ°çŁ¥
    -0.06
    things
    -0.06
    otan
    -0.06
    imper
    -0.06
     things
    -0.06
    伺
    -0.06
    以åħįéĢłæĪIJ
    -0.06
    POSITIVE LOGITS
    ç»ĵæŀľçļĦ
    0.10
    大è¯Ŀ
    0.09
    ancier
    0.09
    çµIJæŀľ
    0.09
    çİĩä½İ
    0.09
     palsu
    0.09
    ç»ĵæŀľè¡¨æĺİ
    0.08
    éĺ³æĢ§
    0.08
    ayers
    0.08
     detections
    0.08
    Activations Density 0.068%

    No Known Activations