© 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. 22440
    Prev
    Next
    INDEX
    Explanations

    Nursery rhymes and fairy tales

    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
    zos
    -0.07
    walker
    -0.07
    ignum
    -0.07
    ewise
    -0.07
    heu
    -0.07
    étrica
    -0.06
    aliza
    -0.06
    rais
    -0.06
    kowski
    -0.06
    plos
    -0.06
    POSITIVE LOGITS
    urt
    0.06
    å¥Ĺ
    0.05
     g
    0.05
     ëĤĺíĥĢ
    0.05
    im
    0.05
    æ
    0.05
    ik
    0.05
    æī
    0.05
    et
    0.04
     there
    0.04
    Activations Density 0.007%

    No Known Activations