© 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. 63164
    Prev
    Next
    INDEX
    Explanations

    box, framed, boxed

    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
    /features
    -0.10
    ä¸įåı¯æĢĿè®®
    -0.08
    çĽĬ
    -0.08
    è··
    -0.08
    onica
    -0.07
    iq
    -0.07
     overhe
    -0.07
    æĪijæĿ¥è¯´ä¸¤åı¥
    -0.07
    /configuration
    -0.07
    -flex
    -0.07
    POSITIVE LOGITS
    -worthy
    0.08
    able
    0.07
    åŃIJéĩĮ
    0.07
     LaTeX
    0.07
    æĸĩæĺİ
    0.06
     punch
    0.06
    edly
    0.06
     result
    0.06
     kết
    0.06
    åĨħçļĦ
    0.06
    Activations Density 0.003%

    No Known Activations