© 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. 61680
    Prev
    Next
    INDEX
    Explanations

    Shakespearean or archaic language

    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
    |int
    -0.09
     LUA
    -0.09
    ä¸įçł´
    -0.08
    çķĻä¸ĭæĿ¥çļĦ
    -0.08
    enberg
    -0.08
     roundup
    -0.08
     OMG
    -0.08
    istico
    -0.08
    æĬ¤æ³ķ
    -0.08
    OMPI
    -0.08
    POSITIVE LOGITS
    ,
    0.07
    katan
    0.06
    æĢĿæĥ³
    0.06
    geld
    0.06
    fetch
    0.06
    c
    0.06
     Venus
    0.06
     Å
    0.06
     men
    0.06
     fetch
    0.06
    Activations Density 0.053%

    No Known Activations