© 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. 44305
    Prev
    Next
    INDEX
    Explanations

    entire / whole

    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
    Negative Logits
    æĢ»è¦ģ
    -0.07
    rome
    -0.07
    Allocator
    -0.07
    {}\
    -0.07
    _ticks
    -0.07
    stand
    -0.07
     freely
    -0.06
    ysz
    -0.06
    ctors
    -0.06
    é¢ij
    -0.06
    POSITIVE LOGITS
     except
    0.12
     entire
    0.12
    except
    0.11
    çļĦä¸Ģèĩ´
    0.11
    ä¸Ģèĩ´
    0.11
    ä¸Ģèĩ´çļĦ
    0.11
     entirety
    0.11
    Except
    0.10
    all
    0.10
    绣ä¸ĢçļĦ
    0.10
    Activations Density 0.224%

    No Known Activations