© 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. 16735
    Prev
    Next
    INDEX
    Explanations

    article followed by noun

    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
     same
    -0.06
    ÙĪد
    -0.06
    atter
    -0.06
     entire
    -0.06
    иÑģÑĤÑĢа
    -0.05
    same
    -0.05
     misma
    -0.05
    ountry
    -0.05
    ä¸ĢåĪĩ
    -0.05
    æķ´ä¸ª
    -0.05
    POSITIVE LOGITS
    inken
    0.07
    еÑģÑĤвÑĥ
    0.06
    ä¸ĩ平米
    0.06
    erven
    0.06
    est
    0.06
    æŶéĹ´æĿ¥
    0.06
     Prise
    0.06
    sher
    0.06
    alore
    0.06
    ests
    0.06
    Activations Density 0.048%

    No Known Activations