© 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. 32251
    Prev
    Next
    INDEX
    Explanations

    Stro age

    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
    -**
    -0.07
    ÄĻc
    -0.07
    Ø¡
    -0.06
    orada
    -0.06
     Loa
    -0.06
    Ïĩο
    -0.06
    NULL
    -0.06
    åıĺæķħ
    -0.06
    ÏĨο
    -0.06
    ermo
    -0.06
    POSITIVE LOGITS
    ilding
    0.07
    oss
    0.07
    æľ¬æĸĩæĿ¥èĩª
    0.07
    opher
    0.07
    wn
    0.07
    ossed
    0.07
    ux
    0.07
    iple
    0.07
    æį
    0.06
    å°¼å°Ķ
    0.06
    Activations Density 0.351%

    No Known Activations