© 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. 57755
    Prev
    Next
    INDEX
    Explanations

    odd or pairs

    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
    CurrentValue
    -0.08
    epsi
    -0.08
    pcf
    -0.08
    iono
    -0.08
    Reference
    -0.08
    ä¸ĸçķĮçļĦ
    -0.08
    ongen
    -0.07
    AILY
    -0.07
    opal
    -0.07
     Reference
    -0.07
    POSITIVE LOGITS
     odd
    0.11
    åģ¶
    0.11
    å¥ĩ
    0.10
     Odd
    0.10
    odd
    0.09
    Odd
    0.09
     pares
    0.08
     ì§
    0.08
    _odd
    0.08
     pairs
    0.07
    Activations Density 0.006%

    No Known Activations