© 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. 16708
    Prev
    Next
    INDEX
    Explanations

    faster, quicker, time, and delivery

    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
    heid
    -0.05
    ä¸ĩå¹´
    -0.05
    pon
    -0.05
    cha
    -0.05
    è¿ij
    -0.05
    å½ĵ代
    -0.05
     invisible
    -0.05
    æĿ¾ä¸ĭ
    -0.05
    åľ°ä¸ĭ
    -0.05
    à¸Ļิ
    -0.05
    POSITIVE LOGITS
    oš
    0.07
    bruck
    0.07
     prot
    0.07
    osas
    0.06
    è¾ľ
    0.06
    antha
    0.06
    tester
    0.06
    jured
    0.06
     Mestre
    0.06
    iento
    0.06
    Activations Density 0.029%

    No Known Activations