© 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. 16605
    Prev
    Next
    INDEX
    Explanations

    date formats (dd/mm, mm/dd)

    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
    ä¸Ģéĩij
    -0.07
     barre
    -0.06
    æŃ·
    -0.06
    urie
    -0.06
    volo
    -0.06
     Ø°
    -0.06
    çī©è¯Ń
    -0.06
    ä¸įè¿ĩè¿Ļ
    -0.05
    èIJ§
    -0.05
    ä¸įæĮ¯
    -0.05
    POSITIVE LOGITS
    ya
    0.06
    æŃ»æ´»
    0.06
    eth
    0.05
     hydration
    0.05
    oving
    0.05
    /
    0.05
    人身å®īåħ¨
    0.05
     viability
    0.05
     suitability
    0.05
    etri
    0.05
    Activations Density 0.008%

    No Known Activations