© 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. 16761
    Prev
    Next
    INDEX
    Explanations

    text ending 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
    gues
    -0.08
     epo
    -0.07
    agli
    -0.07
    ASCII
    -0.07
    quÃŃ
    -0.07
     Gradu
    -0.07
    ç±³é«ĺ
    -0.07
    quem
    -0.07
     (âĢ¦)
    -0.07
    kena
    -0.07
    POSITIVE LOGITS
    '
    0.06
     ever
    0.06
    0.05
    è¡Į
    0.05
     en
    0.05
    "
    0.05
    æķ´
    0.05
     reality
    0.05
    Âł
    0.05
     c
    0.05
    Activations Density 0.021%

    No Known Activations