© 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. 4472
    Prev
    Next
    INDEX
    Explanations

    subtracting or deducting

    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
    æĸ°å®¢æĪ·
    -0.06
    ä¸ĵèIJ¥
    -0.06
    +s
    -0.06
    è·Ľ
    -0.06
    /topics
    -0.06
     Royal
    -0.06
    åħ¼æĢ»ç»ıçIJĨ
    -0.06
     stimmen
    -0.06
    ungan
    -0.06
     STREET
    -0.06
    POSITIVE LOGITS
     subtract
    0.13
     Subtract
    0.12
     subtraction
    0.12
    subtract
    0.11
     deducted
    0.10
     deduct
    0.09
     deduction
    0.09
    æī£éĻ¤
    0.09
    åĩıåİ»
    0.08
    ToRemove
    0.08
    Activations Density 0.027%

    No Known Activations