© 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. 4409
    Prev
    Next
    INDEX
    Explanations

    rings and pack

    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
     ironically
    -0.08
     übrigens
    -0.08
     habis
    -0.07
    åīį人
    -0.07
     fiance
    -0.07
    קר
    -0.07
    ibbon
    -0.07
     bitwise
    -0.07
    egt
    -0.07
    izzo
    -0.07
    POSITIVE LOGITS
    âĢij
    0.12
     ↵
    0.08
    åĽłçĪ²
    0.08
    ophon
    0.07
    âĢIJ
    0.07
    ’
    0.07
    ury
    0.06
    ’s
    0.06
    Ç
    0.06
    屬æĸ¼
    0.06
    Activations Density 0.004%

    No Known Activations