© 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. 25957
    Prev
    Next
    INDEX
    Explanations

    technical or explanatory phrasing

    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
     Sym
    -0.07
    ç¹ģ
    -0.07
    èIJ½ãģ¡
    -0.07
    rowable
    -0.07
    æķ£
    -0.07
    ersist
    -0.07
    ungan
    -0.07
    adou
    -0.07
    subcategory
    -0.07
    eby
    -0.07
    POSITIVE LOGITS
    æľīé£İéĻ©
    0.08
    IPA
    0.08
    åıĪæĢķ
    0.07
    容æĺĵå¼ķèµ·
    0.07
    imes
    0.07
    è¿Ļæł·åģļ
    0.07
    ä¼ļå¼ķèµ·
    0.07
    fra
    0.07
    ipa
    0.06
    roid
    0.06
    Activations Density 0.342%

    No Known Activations