© 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. 16721
    Prev
    Next
    INDEX
    Explanations

    pauses and conjunctions

    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
    Ĭ
    -0.06
    quel
    -0.06
    ca
    -0.06
    cas
    -0.06
    ORY
    -0.06
    una
    -0.06
    æ´ª
    -0.05
    Âł
    -0.05
    vus
    -0.05
    fus
    -0.05
    POSITIVE LOGITS
    etz
    0.06
    atsu
    0.06
    山人海
    0.06
     ...
    0.06
    ê°ĦìĹIJ
    0.06
    amedi
    0.06
    amet
    0.05
    aturi
    0.05
    åħ¨æĸ¹ä½įçļĦ
    0.05
    jenigen
    0.05
    Activations Density 0.058%

    No Known Activations