© 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. 47957
    Prev
    Next
    INDEX
    Explanations

    prosody, stress, intonation, accent

    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
    xmm
    -0.08
    ä¿±è¿Ľ
    -0.08
    erspective
    -0.08
    /interfaces
    -0.08
    VERBOSE
    -0.08
    سÙĬر
    -0.08
    åı£å¾Ħ
    -0.08
    éĢīæĿIJ
    -0.08
     cá»ijt
    -0.08
     Paci
    -0.08
    POSITIVE LOGITS
     syll
    0.07
    éĨĴäºĨ
    0.07
     dá»ĵn
    0.06
     tonic
    0.06
    accent
    0.06
     accent
    0.06
    fony
    0.06
    akan
    0.06
    lev
    0.06
     lev
    0.06
    Activations Density 0.003%

    No Known Activations