© 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. 33391
    Prev
    Next
    INDEX
    Explanations

    centuries and dynasties

    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
     Descar
    -0.08
    .intent
    -0.08
    cock
    -0.08
    å¨ĥå¨ĥ
    -0.08
    posa
    -0.07
     Ritch
    -0.07
     Sting
    -0.07
    éī±
    -0.07
    ÐľÐļ
    -0.07
     Mening
    -0.07
    POSITIVE LOGITS
    åĮĹå®ĭ
    0.11
    å®ĭæľĿ
    0.11
    å®ĭ代
    0.10
    éĻĨ游
    0.10
     Medieval
    0.09
    åįĹå®ĭ
    0.09
    è±ĨæµĨ
    0.08
     medieval
    0.08
     latte
    0.08
    èĢ¶
    0.08
    Activations Density 0.122%

    No Known Activations