© 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. 2502
    Prev
    Next
    INDEX
    Explanations

    herbal teas

    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
    _orient
    -0.08
    .try
    -0.08
     Ø¥Ùħا
    -0.07
    .partial
    -0.07
     entweder
    -0.07
    æµ·æ¶Ľ
    -0.07
    elaar
    -0.07
    ób
    -0.07
    éĶĢåĶ®éĥ¨
    -0.07
    ä»ĸçĶļèĩ³
    -0.07
    POSITIVE LOGITS
    èĻ½çĦ¶åľ¨
    0.10
    èĻ½çĦ¶
    0.09
    çļĦ羣æŃ£
    0.09
    èĻ½
    0.08
    éĽĸçĦ¶
    0.08
     although
    0.08
    èĻ½çĦ¶æĺ¯
    0.08
    羣æŃ£
    0.08
    although
    0.08
     Although
    0.07
    Activations Density 0.096%

    No Known Activations