© 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. 20220
    Prev
    Next
    INDEX
    Explanations

    exactly subtract

    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
    ä¾ĽåºĶ产åĵģ
    -0.08
    å¸Īå¼Ł
    -0.08
    ebu
    -0.08
    kog
    -0.07
     routi
    -0.07
     ÐļалÑĥ
    -0.07
    å·¡è§Ĩåijĺ
    -0.07
    meros
    -0.07
    idity
    -0.07
     kelu
    -0.07
    POSITIVE LOGITS
     Gallagher
    0.09
     subtract
    0.07
    exact
    0.07
     Subtract
    0.07
     exact
    0.07
    _exact
    0.07
     Exact
    0.07
    hend
    0.07
    phant
    0.06
    Exact
    0.06
    Activations Density 0.001%

    No Known Activations