© 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. 4092
    Prev
    Next
    INDEX
    Explanations

    scientific notation or email addresses

    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
    aris
    -0.08
    veu
    -0.07
    åıijè¡ĮçļĦ
    -0.07
    ÐĵС
    -0.07
    utex
    -0.07
    ׼×Ŀ
    -0.07
    aret
    -0.07
    ìĥī
    -0.07
    -abortion
    -0.07
    IENTATION
    -0.07
    POSITIVE LOGITS
    级
    0.07
    typ
    0.07
    æĻ®åıĬ
    0.06
    级çļĦ
    0.06
     exponential
    0.06
    à¯ģà®®à¯į
    0.06
    tera
    0.06
    ilog
    0.06
    æĮĩ
    0.06
    erg
    0.06
    Activations Density 0.001%

    No Known Activations