© 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. 30441
    Prev
    Next
    INDEX
    Explanations

    Etch-a-Sketch, polarization, hot Jupiters, Parks and Recreation

    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
    ).**
    -0.06
    -0.06
    ]}
    -0.06
    |
    -0.06
    ).
    -0.06
     [
    -0.06
     /
    -0.06
    "%(
    -0.06
    %
    -0.05
    POSITIVE LOGITS
    éĺ¿æĭī伯
    0.11
    æĸ°åĬłåĿ¡
    0.10
    åħ¢åħ¢ä¸ļä¸ļ
    0.09
    èĢ³çĨŁèĥ½è¯¦
    0.09
    åĭĩå¾Ģ缴åīį
    0.09
    <"
    0.09
    çĽ¸ä¼¼æĸĩçĮ®
    0.08
    *”
    0.08
    ãĢģ“
    0.08
    #__
    0.08
    Activations Density 0.195%

    No Known Activations