© 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. 16601
    Prev
    Next
    INDEX
    Explanations

    asynchronous Sport zero patch

    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
    comb
    -0.07
     Gecko
    -0.06
    å®ļ为
    -0.06
    fen
    -0.06
    _interfaces
    -0.06
     Comb
    -0.05
    表
    -0.05
    ariamente
    -0.05
    lý
    -0.05
    chau
    -0.05
    POSITIVE LOGITS
     Alternativ
    0.05
    Ñģле
    0.05
    stech
    0.05
    unto
    0.05
    tih
    0.05
    iffer
    0.05
    ”âĢ¦
    0.05
    porno
    0.05
     sop
    0.05
    åıijè§ī
    0.05
    Activations Density 0.001%

    No Known Activations