© 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. 41329
    Prev
    Next
    INDEX
    Explanations

    subtracting, dividing, cancelling

    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
    HashCode
    -0.08
    #w
    -0.08
    åħīæĺ¯
    -0.07
    ippet
    -0.07
    inach
    -0.07
    ç¨įæľī
    -0.07
    adop
    -0.07
     rasse
    -0.07
    å¥
    -0.07
    Utf
    -0.07
    POSITIVE LOGITS
    èĸĦ
    0.08
    ziv
    0.06
    æĥij
    0.06
    èıĮ
    0.06
    缼
    0.06
    æĹłäºĭ
    0.06
    à¹Ģหลืà¸Ń
    0.06
    ä½Ļ
    0.06
     homogeneous
    0.06
     виÑĤа
    0.06
    Activations Density 0.002%

    No Known Activations