© 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. 62235
    Prev
    Next
    INDEX
    Explanations

    percentages, years, or measurements

    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
    lette
    -0.07
    !:
    -0.07
    æĹ¢çĦ¶
    -0.07
    ?:
    -0.06
     semb
    -0.06
    ByName
    -0.06
    åľĥ
    -0.06
    ieno
    -0.06
    âme
    -0.06
    à¹Īà¸Ńย
    -0.06
    POSITIVE LOGITS
    å¹³åĿĩ
    0.07
    çļĦå¹³åĿĩ
    0.07
    ä¸įåı¯æĢĿè®®
    0.07
    å¤ľéĹ´
    0.07
    unker
    0.07
    æݪ置
    0.07
    é«
    0.07
    ¬
    0.07
    ëłģ
    0.07
    åİĨæŶ
    0.07
    Activations Density 0.300%

    No Known Activations