© 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. 16780
    Prev
    Next
    INDEX
    Explanations

    def

    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
    usen
    -0.05
     more
    -0.05
    amed
    -0.05
     cad
    -0.05
    K
    -0.05
    ä¿¡
    -0.05
     be
    -0.05
    quer
    -0.04
    erv
    -0.04
    eny
    -0.04
    POSITIVE LOGITS
    isse
    0.07
     bénévoles
    0.07
    ovin
    0.06
    ä¹ĭä¸į
    0.06
    ático
    0.06
     untranslated
    0.06
    fru
    0.06
    rine
    0.06
    -contrib
    0.06
    ÑħодÑıÑĤ
    0.06
    Activations Density 0.048%

    No Known Activations