© 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. 19675
    Prev
    Next
    INDEX
    Explanations

    computed tomography (CT) scans

    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
    ä¸ĩå²ģ
    -0.08
    PHPExcel
    -0.07
    ä¹ĭæĢ¥
    -0.07
    åģ¥åħ¨
    -0.07
    amples
    -0.07
     dadurch
    -0.07
    æľ¬ç½ij
    -0.07
    пÑĢÑĭ
    -0.07
    dling
    -0.07
    è¿ĩ渡
    -0.06
    POSITIVE LOGITS
     abnormalities
    0.08
     scans
    0.08
     findings
    0.08
     scan
    0.08
    éĺħ
    0.08
    å½±åĥı
    0.08
    ä»ĭåħ¥
    0.07
    å½±åĥıåѦ
    0.07
     examination
    0.07
    æī«æıı
    0.07
    Activations Density 0.359%

    No Known Activations