© 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. 22547
    Prev
    Next
    INDEX
    Explanations

    inscriptions and symbols

    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
     sustain
    -0.06
    å¦ĤåĽł
    -0.06
     sust
    -0.06
     sustaining
    -0.06
    ucz
    -0.06
     duy
    -0.05
    alnız
    -0.05
     grounded
    -0.05
    миÑĢ
    -0.05
    ç»´æĮģåľ¨
    -0.05
    POSITIVE LOGITS
    iose
    0.06
    交åıī
    0.06
    abwe
    0.06
    åIJİä¸ĸ
    0.05
    amaan
    0.05
    迦
    0.05
     kode
    0.05
    Repeated
    0.05
     code
    0.05
     IDEA
    0.05
    Activations Density 0.002%

    No Known Activations