© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 4615
    Prev
    Next
    INDEX
    Explanations

    description of entities

    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
    éĥ½åįģåĪĨ
    -0.09
     невозмо
    -0.08
    éĥ½ä¼ļæľī
    -0.08
     наÑĩалаÑģÑĮ
    -0.08
     позволÑıÑĤ
    -0.08
    ä¹Łä¸įå°ij
    -0.08
     ÑĥвеÑĢенÑĭ
    -0.08
    éĥ½å¾Ī好
    -0.08
     significa
    -0.08
    çļĦè¿ĺæľī
    -0.08
    POSITIVE LOGITS
     is
    0.10
     can
    0.08
     indeed
    0.08
     itself
    0.08
     may
    0.08
    ä¹ĭæīĢ以
    0.08
     adalah
    0.08
     reportedly
    0.08
     undergo
    0.08
     are
    0.07
    Activations Density 1.367%

    No Known Activations