© 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. 1618
    Prev
    Next
    INDEX
    Explanations

    common denominator, greatest common factor

    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
     later
    -0.07
    对ä»ĸ们çļĦ
    -0.07
    ouns
    -0.06
     اÙĦÙħز
    -0.06
    IRON
    -0.06
    çļĦä»ĸ
    -0.06
    ovens
    -0.06
    ward
    -0.06
    æľīäºĨ
    -0.06
    çľĭåĪ°ä»ĸ
    -0.06
    POSITIVE LOGITS
     reportedly
    0.07
    âĺħâĺĨ
    0.07
     *__
    0.07
    çļĦè¯Ŀé¢ĺ
    0.07
    -ever
    0.06
    çĶµèĦijçīĪ
    0.06
     Wayne
    0.06
     ever
    0.06
    axe
    0.06
    à¸Ķุ
    0.06
    Activations Density 0.911%

    No Known Activations