© 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. 2241
    Prev
    Next
    INDEX
    Explanations

    architectural features

    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
    彬彬
    -0.07
     Slut
    -0.07
    ä»Ļåīij
    -0.07
    à¸Ńà¸Ļ
    -0.07
     thái
    -0.07
     aktuell
    -0.07
    åĨ°å±±
    -0.07
     targeted
    -0.06
    åĽŃè·¯
    -0.06
    ivers
    -0.06
    POSITIVE LOGITS
    ä¸Ń央
    0.09
     central
    0.08
     quatre
    0.08
    åľ¨ä¸»
    0.08
    edic
    0.08
     rectangular
    0.08
    æĪijæľĢåĸľæ¬¢
    0.07
    chsel
    0.07
    False
    0.07
    lanjut
    0.07
    Activations Density 0.124%

    No Known Activations