© 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. 45771
    Prev
    Next
    INDEX
    Explanations

    minus subtraction

    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
    åıĻ
    -0.07
    ÏĦίαÏĤ
    -0.07
     Äija
    -0.07
    minen
    -0.07
    embl
    -0.07
    wargs
    -0.07
    allee
    -0.07
    æµ·é»ĺ
    -0.07
    Callbacks
    -0.07
    XL
    -0.07
    POSITIVE LOGITS
     minus
    0.19
    åĩıåİ»
    0.18
    minus
    0.16
    -minus
    0.14
     subtract
    0.13
    Minus
    0.13
    å·®
    0.13
     минÑĥÑģ
    0.12
    _minus
    0.12
     Subtract
    0.12
    Activations Density 0.069%

    No Known Activations