© 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. 22556
    Prev
    Next
    INDEX
    Explanations

    he/they followed by a word

    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
    æݲ
    -0.07
    imt
    -0.07
    ãĤĴãģĭãģijãģ¦
    -0.07
     Wszystko
    -0.07
    ionali
    -0.07
    äºĭå¾Į
    -0.06
    żu
    -0.06
    夥
    -0.06
     kapit
    -0.06
    iscipl
    -0.06
    POSITIVE LOGITS
    Âł
    0.05
     &
    0.05
     P
    0.05
     Go
    0.05
    daten
    0.05
     that
    0.05
    âĢ¦it
    0.05
     estrem
    0.05
     gor
    0.05
     âĢ¦
    0.05
    Activations Density 0.019%

    No Known Activations