© 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. 64376
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis followed by code/math

    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
    æ¯ıæĪ·
    -0.07
    olo
    -0.07
    ipa
    -0.07
    æĮij
    -0.06
    çī
    -0.06
     пого
    -0.06
    çĿģ
    -0.06
    ä»°
    -0.06
    Ãło
    -0.06
    å±ķ
    -0.06
    POSITIVE LOGITS
     rass
    0.08
     Ingram
    0.07
    orong
    0.07
    ouvr
    0.07
    群éĽĦ
    0.07
    ooks
    0.07
    çļĦ身æĿIJ
    0.07
    undos
    0.07
    ArrayOf
    0.07
    gente
    0.07
    Activations Density 0.011%

    No Known Activations