© 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. 831
    Prev
    Next
    INDEX
    Explanations

    you can

    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
     lòng
    -0.07
    aber
    -0.07
     Mód
    -0.06
    ickers
    -0.06
    losion
    -0.06
     pula
    -0.06
     nam
    -0.06
    skar
    -0.06
    Pipeline
    -0.06
    èĵĿæµ·
    -0.06
    POSITIVE LOGITS
    å±ķå¼Ģåħ¨éĥ¨
    0.08
    ÙĴÙĬ
    0.07
     indeed
    0.07
     dasarnya
    0.07
    èĤī
    0.07
    _From
    0.07
     simply
    0.07
    è®¤è®¤çľŁçľŁ
    0.07
    oretical
    0.07
    ä¸įèµ·
    0.07
    Activations Density 0.446%

    No Known Activations