© 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. 16633
    Prev
    Next
    INDEX
    Explanations

    42

    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
    éĻIJäºİ
    -0.08
    er
    -0.07
    etheless
    -0.06
    gat
    -0.06
    ëŀĺ
    -0.06
    mate
    -0.06
    igneur
    -0.06
    ؤÙĦاء
    -0.06
    жеÑĤ
    -0.06
    uarios
    -0.06
    POSITIVE LOGITS
    ש×Ķ
    0.07
    ä¸įåĸĦ
    0.07
    stein
    0.07
    Ø©
    0.06
    ós
    0.06
    yang
    0.06
    ic
    0.06
    icul
    0.06
    liest
    0.06
    度
    0.06
    Activations Density 0.061%

    No Known Activations