© 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. 16898
    Prev
    Next
    INDEX
    Explanations

    deal/coming out

    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
    Not in Any Lists

    No Comments

    Negative Logits
    èĦ¸
    -0.06
    yta
    -0.06
     ÑģооÑĤвеÑĤÑģÑĤвÑĥ
    -0.06
     ning
    -0.06
    -&
    -0.06
    ående
    -0.05
    oving
    -0.05
     ident
    -0.05
     statuses
    -0.05
    ]+)/
    -0.05
    POSITIVE LOGITS
    arvi
    0.06
    ä¹Łä¸įè¦ģ
    0.06
    hip
    0.06
    ØŃ
    0.05
    ØŁ
    0.05
    ç§ijæĬĢåŀĭ
    0.05
     beg
    0.05
    beg
    0.05
    æ²³éķĩ
    0.05
    ho
    0.05
    Activations Density 0.003%

    No Known Activations