© 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. 16767
    Prev
    Next
    INDEX
    Explanations

    regex patterns or url structures

    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
    onton
    -0.06
    Cast
    -0.06
    å¹´ç»ıéªĮ
    -0.06
    aji
    -0.05
     correspond
    -0.05
     Aleman
    -0.05
    解ç¦ģ
    -0.05
     Unidades
    -0.05
    ursal
    -0.05
    æķ°æį®è¿Ľè¡Į
    -0.05
    POSITIVE LOGITS
    uguay
    0.06
    æī
    0.06
    önen
    0.06
    dish
    0.05
    мÑĥÑĤ
    0.05
    ön
    0.05
    tid
    0.05
    è¿Ń
    0.05
    ãģ£ãģ½
    0.05
    ukti
    0.05
    Activations Density 0.036%

    No Known Activations