© 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. 25847
    Prev
    Next
    INDEX
    Explanations

    office, Insurance, Title, Delivery, post

    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
    igem
    -0.08
     Pfeffer
    -0.08
    rane
    -0.07
     Contractor
    -0.07
    ×ĵ×Ŀ
    -0.07
    ersi
    -0.07
    ersen
    -0.07
    é¼»åŃĶ
    -0.07
    港澳
    -0.06
    æ¶īç¨İ
    -0.06
    POSITIVE LOGITS
    èµİ
    0.08
    iss
    0.07
    STS
    0.07
    æĹłäºº
    0.07
    åįıåĴĮ
    0.07
    éĩijåŁİ
    0.07
    wand
    0.06
    SSL
    0.06
    éĻ©
    0.06
    _initialized
    0.06
    Activations Density 0.003%

    No Known Activations