© 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. 26180
    Prev
    Next
    INDEX
    Explanations

    fractions and numbers

    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
    æīĢæľª
    -0.07
    ig
    -0.06
     Hut
    -0.06
    åIJĦ
    -0.06
    ï¼Ī
    -0.06
    ence
    -0.05
    ç¥Ł
    -0.05
     weir
    -0.05
     traceback
    -0.05
    ä¹ĭ以
    -0.05
    POSITIVE LOGITS
    ży
    0.08
    bab
    0.08
    ysi
    0.08
    باب
    0.08
    bag
    0.08
    /rfc
    0.08
    ayar
    0.07
    注æĦıäºĨ
    0.07
    AZE
    0.07
    GRE
    0.07
    Activations Density 0.001%

    No Known Activations