© 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. 61326
    Prev
    Next
    INDEX
    Explanations

    japonica, communis, cordifolia, officinale

    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
    们
    -0.07
    ulam
    -0.07
     Legislativo
    -0.07
    éħİ
    -0.07
    éĺµ
    -0.07
    ä»¬ä¹Ł
    -0.07
     Geg
    -0.07
    åĪ«è®©
    -0.06
    ILA
    -0.06
    ضÙħ
    -0.06
    POSITIVE LOGITS
    ensis
    0.09
    åı¯åĸľ
    0.08
    yai
    0.07
    freund
    0.07
    âĢİ
    0.07
    ÙĪÙĨÙĬØ©
    0.07
    vá
    0.07
    æµĭå®ļ仪
    0.07
    aho
    0.07
    åıĪåIJį
    0.06
    Activations Density 0.161%

    No Known Activations