© 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. 22842
    Prev
    Next
    INDEX
    Explanations

    separating clauses or continuing sentences

    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
    oupper
    -0.07
    ’n
    -0.07
    ire
    -0.07
    ئÛĮ
    -0.07
    ourcing
    -0.07
    ίÏīν
    -0.07
    æĪIJ群
    -0.06
    _secure
    -0.06
    acional
    -0.06
    åĽ¾çīĩæĿ¥æºIJäºİç½ij绾
    -0.06
    POSITIVE LOGITS
    çŃīçŃī
    0.09
    âĢ¦ãĢĤ
    0.08
    âĢ¦but
    0.08
    âĢ¥
    0.07
    oh
    0.07
    âĢ¦
    0.07
    .Done
    0.07
    ,...
    0.07
    kin
    0.07
    âĢ¦.
    0.07
    Activations Density 0.125%

    No Known Activations