© 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. 22414
    Prev
    Next
    INDEX
    Explanations

    offer or present

    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
     tán
    -0.06
    opera
    -0.06
    æݧèĤ¡
    -0.06
    ãģ®ãģ¨
    -0.06
    Opera
    -0.06
    ibera
    -0.06
     revient
    -0.06
     ÙģÙĬÙĩ
    -0.05
    æı¡çĿĢ
    -0.05
    recent
    -0.05
    POSITIVE LOGITS
    acle
    0.06
    æĭĽ
    0.06
    rag
    0.05
    ANG
    0.05
    大èĩªçĦ¶
    0.05
    èĩªçĦ¶çģ¾å®³
    0.05
    è¯Ń
    0.05
    gestellt
    0.05
    ang
    0.05
    æĬĬæīĭ
    0.05
    Activations Density 0.008%

    No Known Activations