© 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. 16662
    Prev
    Next
    INDEX
    Explanations

    commenting on details

    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
    å¼¥
    -0.05
    paro
    -0.05
     UserID
    -0.05
    chow
    -0.05
     version
    -0.05
    é¢ĨæĤŁ
    -0.05
    å±¥è¡ĮèģĮè´£
    -0.05
    etro
    -0.05
    æľ¬åħ¬åı¸
    -0.05
    åijĬè¯īä»ĸ
    -0.05
    POSITIVE LOGITS
     gul
    0.06
     atmospheric
    0.06
     atmosfer
    0.06
     Atmospheric
    0.05
    ofil
    0.05
    mosph
    0.05
    иж
    0.05
     аÑĤмоÑģÑĦеÑĢ
    0.05
    obre
    0.05
     atmosf
    0.05
    Activations Density 0.008%

    No Known Activations