© 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. 33709
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with numbers and operators

    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
    ç¾¹
    -0.07
    º
    -0.07
    tte
    -0.07
    &A
    -0.06
     ste
    -0.06
    BUF
    -0.06
    è¡¥åĬ©è´¹
    -0.06
    toon
    -0.06
    åıĺåĮĸåĴĮ
    -0.06
    å¤ļç§įå½¢å¼ı
    -0.06
    POSITIVE LOGITS
    çĬ
    0.08
    æ±Ĥç²¾
    0.08
     ës
    0.07
    _targets
    0.07
    éz
    0.07
    人åĽŀå¤į
    0.07
    زش
    0.07
    Ether
    0.07
    èv
    0.07
     thắt
    0.07
    Activations Density 0.018%

    No Known Activations