© 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. 22383
    Prev
    Next
    INDEX
    Explanations

    parentheses and 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
    olini
    -0.07
    ahah
    -0.07
    lán
    -0.06
     cim
    -0.06
    ç»ĵæŀĦçļĦ
    -0.06
     **—
    -0.06
    ×¢×Ļ
    -0.06
     bilÉĻ
    -0.06
    late
    -0.06
    ideos
    -0.06
    POSITIVE LOGITS
     proceeds
    0.05
    ross
    0.05
     CáºŃn
    0.05
     exatamente
    0.05
    Tank
    0.05
    ìľ
    0.05
    дÑĢо
    0.05
    obl
    0.05
     spec
    0.05
    æ¯Ķéĩį
    0.05
    Activations Density 0.012%

    No Known Activations