© 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. 38258
    Prev
    Next
    INDEX
    Explanations

    advertising and ads

    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
    ì±ħìĿĦ
    -0.07
    ä¸į移
    -0.07
    å¼ĢæĶ¾çļĦ
    -0.07
    ãģªãĤīãģļ
    -0.07
    lassian
    -0.07
    ainter
    -0.07
    جÙĦÙĬ
    -0.07
    mapped
    -0.07
     SSH
    -0.06
    .nasa
    -0.06
    POSITIVE LOGITS
    -inline
    0.09
    广åijĬçļĦ
    0.09
    ä¸ĢåĪĻ
    0.09
    广åijĬ
    0.08
    vertis
    0.08
    erst
    0.08
     ads
    0.08
    ads
    0.08
    æĽ¿
    0.08
    vertising
    0.08
    Activations Density 0.124%

    No Known Activations