© 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. 40074
    Prev
    Next
    INDEX
    Explanations

    subtraction and arithmetic expressions

    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
    adis
    -0.08
    ahl
    -0.08
    å¥Ħ
    -0.08
    гей
    -0.08
    pth
    -0.07
    æĥľ
    -0.07
    VERSE
    -0.07
    _volume
    -0.07
    èº
    -0.07
    oyer
    -0.07
    POSITIVE LOGITS
    åº
    0.07
    å·®
    0.07
    retain
    0.07
     subtraction
    0.07
    å°½æľī
    0.07
     removal
    0.06
    Cancellation
    0.06
    ä¹ĭå·®
    0.06
    åĨįåİ»
    0.06
     à¹Ģหล
    0.06
    Activations Density 0.020%

    No Known Activations