© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22517
    Prev
    Next
    INDEX
    Explanations

    pronouncement or pronounces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    æĮĩ
    -0.05
    éĿ¢åIJij
    -0.05
    rop
    -0.05
     Tier
    -0.05
    terr
    -0.05
    ear
    -0.05
    cher
    -0.05
    级
    -0.05
     Gr
    -0.05
    æĺ¯æĮĩ
    -0.04
    POSITIVE LOGITS
    anty
    0.08
    ungle
    0.07
    HAND
    0.07
    rådet
    0.07
    -pencil
    0.07
    Others
    0.06
    ergi
    0.06
    vány
    0.06
    -Men
    0.06
     geler
    0.06
    Activations Density 0.001%

    No Known Activations