© 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. 24144
    Prev
    Next
    INDEX
    Explanations

    words about something new

    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
    åĴĮéĶĢåĶ®
    -0.08
    ož
    -0.08
    pell
    -0.08
    füh
    -0.08
    wann
    -0.08
    hares
    -0.08
    anjian
    -0.08
    igny
    -0.08
    гоÑĢе
    -0.08
    å¼ı设计
    -0.07
    POSITIVE LOGITS
    ly
    0.10
    à¹Ĩ
    0.08
    ness
    0.08
    (er
    0.07
    ç¨ĭ度çļĦ
    0.07
    Âł
    0.07
    æĹłæ¯ĶçļĦ
    0.07
    æĹłäºĭ
    0.07
    æĢ§çļĦ
    0.07
     à¹Ĩ
    0.07
    Activations Density 0.141%

    No Known Activations