© 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. 50490
    Prev
    Next
    INDEX
    Explanations

    silver, bronze, gold medal

    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
    åĪ°åºŃ
    -0.07
     unset
    -0.07
    åħ·æľīçļĦ
    -0.06
    à¹Ģหย
    -0.06
    ä¸Ĭä¸į
    -0.06
    ç§ijåѦéĻ¢
    -0.06
    Lv
    -0.06
    igos
    -0.06
    mill
    -0.06
    /css
    -0.06
    POSITIVE LOGITS
     beiden
    0.08
    áĥIJ
    0.07
     Abschluss
    0.07
     تÙħاÙħاÙĭ
    0.06
    ijat
    0.06
    imal
    0.06
    noc
    0.06
     natomiast
    0.06
     consolation
    0.06
     sostanzi
    0.06
    Activations Density 0.196%

    No Known Activations