© 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. 55541
    Prev
    Next
    INDEX
    Explanations

    restricts / restricted

    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
    ä¸ŃéĢļ
    -0.07
    è½®åĽŀ
    -0.07
     stuffing
    -0.06
    LocalizedString
    -0.06
    letz
    -0.06
    illard
    -0.06
    ä½ıæĪ¿åŁİ乡建设
    -0.06
    浩
    -0.06
    तर
    -0.06
     lumber
    -0.06
    POSITIVE LOGITS
     onto
    0.08
    enha
    0.08
    osso
    0.08
    onsor
    0.08
     Ank
    0.08
    RAF
    0.07
     Schwe
    0.07
     داÙħ
    0.07
    onaut
    0.07
    ä¸Ĭä¸Ģ页
    0.07
    Activations Density 0.004%

    No Known Activations