© 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. 16620
    Prev
    Next
    INDEX
    Explanations

    end of sentence 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
    then
    -0.06
    æĥħåĨµè¯´æĺİ
    -0.05
    éģ½
    -0.05
    antas
    -0.05
    ç¥ĸæ¯į
    -0.05
    Âł
    -0.05
    ux
    -0.05
    èįĢ
    -0.05
    ickle
    -0.05
    arrant
    -0.05
    POSITIVE LOGITS
    ophobia
    0.07
    åĽ´ç»ķçĿĢ
    0.06
    æķĪåºĶ
    0.06
    临
    0.06
    BOUND
    0.06
    管好
    0.06
    ذار
    0.06
    اÙĦÙĬØ©
    0.05
    Fo
    0.05
     amb
    0.05
    Activations Density 0.068%

    No Known Activations