© 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. 17683
    Prev
    Next
    INDEX
    Explanations

    pronunciation and accents

    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
     outnumber
    -0.07
    _DECLARE
    -0.07
     агÑĢе
    -0.07
    罪åIJį
    -0.07
    unde
    -0.07
    éĢīé¢ĺ
    -0.07
     Pool
    -0.07
    çļĦ被
    -0.07
    æİĸ
    -0.07
    .dom
    -0.07
    POSITIVE LOGITS
     pronunciation
    0.13
     phon
    0.11
     vowel
    0.11
     syll
    0.11
     vowels
    0.10
    åıijéŁ³
    0.10
    åı£éŁ³
    0.10
     accent
    0.10
     pronunci
    0.09
     spoken
    0.09
    Activations Density 0.040%

    No Known Activations