© 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. 3391
    Prev
    Next
    INDEX
    Explanations

    verbal communication and 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
    iddy
    -0.07
    unta
    -0.07
    ezz
    -0.07
    HeaderValue
    -0.07
    ĩ´
    -0.07
    agod
    -0.06
    éĿĴæĿ¾
    -0.06
    zare
    -0.06
    æĦŁãĤĴ
    -0.06
    -wide
    -0.06
    POSITIVE LOGITS
    æĸĩåŃĹ
    0.10
     verbal
    0.09
    /text
    0.09
    æĸĩåŃĹçļĦ
    0.09
     text
    0.09
    åĴĮåĽ¾çīĩ
    0.09
    çļĦæĸĩåŃĹ
    0.09
    -language
    0.08
    æĸĩæľ¬
    0.08
     spoken
    0.08
    Activations Density 0.379%

    No Known Activations