© 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. 30978
    Prev
    Next
    INDEX
    Explanations

    determines or compares subsets

    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
    两级
    -0.08
    idd
    -0.08
    aley
    -0.07
    brit
    -0.07
    uran
    -0.07
    éĦī
    -0.07
    retval
    -0.07
    åIJīæĸ¯
    -0.07
    åıĪ好
    -0.07
    ingan
    -0.07
    POSITIVE LOGITS
     closest
    0.11
     subset
    0.11
    ä¸ŃæľĢ
    0.11
    åħ¶ä¸ŃæľĢ
    0.10
    closest
    0.10
    æľĢåħ·
    0.09
     Subset
    0.09
    ãģ®ä¸Ģéĥ¨
    0.09
    ä¸ŃçļĦä¸Ģ个
    0.09
     nearest
    0.09
    Activations Density 0.277%

    No Known Activations