© 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. 34026
    Prev
    Next
    INDEX
    Explanations

    resistance and opposing forces

    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
    æĥĬéŃĤ
    -0.08
    ä¸įçĶ¨åĨį
    -0.07
    кÑĥлÑĮÑĤ
    -0.07
    ouses
    -0.07
    aszt
    -0.06
    Ĵ·
    -0.06
    неÑģ
    -0.06
    OUSE
    -0.06
    дно
    -0.06
    åĩºäºĭ
    -0.06
    POSITIVE LOGITS
    éĺ»
    0.11
    æĬµæĬĹ
    0.11
     resisting
    0.11
    éĺ»æŃ¢
    0.11
    éĺ»ç¢į
    0.10
     opposes
    0.10
     oppose
    0.10
    éĺ»åĬĽ
    0.10
     resistance
    0.10
     opposing
    0.09
    Activations Density 0.011%

    No Known Activations