© 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. 1716
    Prev
    Next
    INDEX
    Explanations

    numbers following counts

    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
    常
    -0.07
    é¢ľ
    -0.06
    .Compile
    -0.06
    udu
    -0.06
    cil
    -0.06
    cision
    -0.06
    -selection
    -0.06
    ίκ
    -0.06
    迹
    -0.06
     oport
    -0.06
    POSITIVE LOGITS
    åħ¶ä»ĸ人çļĦ
    0.11
     others
    0.09
    åľ¨è¿Ļæĸ¹éĿ¢
    0.09
     theirs
    0.09
    CHA
    0.08
    æľīçļĦ
    0.08
    æľīçļĦæĺ¯
    0.08
    Others
    0.08
    others
    0.08
    æľīçļĦåľ¨
    0.08
    Activations Density 0.053%

    No Known Activations