© 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. 16681
    Prev
    Next
    INDEX
    Explanations

    code punctuation};)

    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
    iskey
    -0.07
    érc
    -0.07
     Sâm
    -0.06
    atrième
    -0.06
    identes
    -0.06
    çĻ½éĩij
    -0.06
    emberg
    -0.06
    åĽ¢éĺŁåIJĪä½ľç²¾ç¥ŀ
    -0.06
    oare
    -0.06
    reto
    -0.06
    POSITIVE LOGITS
    nung
    0.06
    大æĦı
    0.05
     Le
    0.05
    riors
    0.05
    ec
    0.05
     South
    0.05
     wards
    0.05
    å¾Īåı¯èĥ½
    0.04
    è¦ģä¹Ī
    0.04
     North
    0.04
    Activations Density 0.007%

    No Known Activations