© 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. 50711
    Prev
    Next
    INDEX
    Explanations

    logical operations

    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
    åĪĩå®ŀåģļ好
    -0.07
    çŃĭ
    -0.06
    rafa
    -0.06
    æģĻ
    -0.06
    åĨĬ
    -0.06
    /Area
    -0.06
     scaled
    -0.06
    éĩįåĬĽ
    -0.06
    scaled
    -0.06
    è¿ĻäºĽæķ°æį®
    -0.06
    POSITIVE LOGITS
    Truth
    0.10
    éĢ»è¾ij
    0.09
    çļĦéĢ»è¾ij
    0.09
     Truth
    0.09
     Logic
    0.09
     truth
    0.09
     диз
    0.09
    trut
    0.09
     Logical
    0.09
     logic
    0.09
    Activations Density 0.012%

    No Known Activations