© 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. 56668
    Prev
    Next
    INDEX
    Explanations

    subtract from, less than

    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
    arze
    -0.07
    джи
    -0.07
    umble
    -0.07
    Êľ
    -0.07
     Howe
    -0.07
    ä¸įæĽ¾
    -0.07
    åıŃ
    -0.07
     strcat
    -0.07
    è¿Ļæł·çļĦæĥħåĨµ
    -0.07
    ä¸įå¸ĮæľĽ
    -0.07
    POSITIVE LOGITS
    éĩİèĽ®
    0.07
    iaire
    0.07
    cket
    0.06
     muka
    0.06
    idor
    0.06
    è¤
    0.06
    æĤ¶
    0.06
     sup
    0.06
    å¤Ħ女座
    0.06
     itself
    0.06
    Activations Density 0.008%

    No Known Activations