© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9036
    Prev
    Next
    INDEX
    Explanations

    lead or margin

    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
    ansir
    -0.08
    èijĨ
    -0.07
    æ¯Ģ
    -0.07
    æĴ¼
    -0.07
    leftrightarrow
    -0.07
    elij
    -0.07
    frequ
    -0.07
    à¸Ĺัà¸Ķ
    -0.07
    åĩĨ
    -0.07
    é¥
    -0.07
    POSITIVE LOGITS
     positive
    0.12
     Positive
    0.11
    -positive
    0.10
    positive
    0.10
    Positive
    0.10
     positif
    0.10
     positivo
    0.09
     positivos
    0.09
    _positive
    0.09
    为æŃ£
    0.09
    Activations Density 0.039%

    No Known Activations