© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30212
    Prev
    Next
    INDEX
    Explanations

    geometric and physical structures

    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
    stv
    -0.10
    /apple
    -0.08
     tenden
    -0.08
    èĮĥåĽ´åĨħ使çĶ¨
    -0.08
    éĢļè¿ĩ使çĶ¨
    -0.08
    AndView
    -0.08
    hyth
    -0.08
    edah
    -0.08
    ä¾łå®¢
    -0.08
    ä¸Ģèµ·æĿ¥çľĭçľĭåIJ§
    -0.08
    POSITIVE LOGITS
    enberg
    0.08
     prism
    0.07
     Prism
    0.06
    esis
    0.06
    pr
    0.06
     Pr
    0.06
     "
    0.06
    æĿ¡
    0.06
    åIJİ人
    0.06
    0.06
    Activations Density 0.031%

    No Known Activations