© 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. 11447
    Prev
    Next
    INDEX
    Explanations

    phonetics and transliteration

    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
    ness
    -0.09
    ì§ij
    -0.07
    itters
    -0.07
    NESS
    -0.07
    oins
    -0.06
    ÙĩÙī
    -0.06
    æĹłä¸º
    -0.06
    psilon
    -0.06
    urant
    -0.06
    utant
    -0.06
    POSITIVE LOGITS
     conson
    0.09
     pronunciation
    0.08
    ault
    0.08
    phon
    0.08
    etically
    0.08
     spell
    0.08
     phon
    0.08
    spell
    0.08
     Phon
    0.08
    åŃĹæ¯į
    0.08
    Activations Density 0.013%

    No Known Activations