© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 51500
    Prev
    Next
    INDEX
    Explanations

    placeholder

    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
    å±ĪæĮĩ
    -0.07
     Zip
    -0.07
    ç¼ł
    -0.07
    ãĥªãĥ¼
    -0.07
    Zip
    -0.07
    à´¤àµįà´¤
    -0.07
    ç»ķ
    -0.07
    Requested
    -0.07
     Checked
    -0.06
    antino
    -0.06
    POSITIVE LOGITS
     placeholder
    0.11
     placeholders
    0.10
    模æĿ¿
    0.10
     Placeholder
    0.09
    ä¸İå®ŀéĻħ
    0.09
    Replace
    0.09
     generic
    0.09
    模çīĪ
    0.09
     Replace
    0.08
    -generic
    0.08
    Activations Density 0.087%

    No Known Activations