© 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. 22275
    Prev
    Next
    INDEX
    Explanations

    forced to

    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
    okr
    -0.07
    à¸Ńยà¹Īาà¸ĩà¹Ħมà¹Īà¸ĸูà¸ģà¸ķà¹īà¸Ńà¸ĩ
    -0.07
    /Gate
    -0.07
    .DriverManager
    -0.07
     undermin
    -0.07
    erken
    -0.07
    odore
    -0.07
    ÑģÑĤÑĢой
    -0.06
     filmer
    -0.06
    ç©Į
    -0.06
    POSITIVE LOGITS
    è¿«
    0.06
     forced
    0.06
    迫使
    0.06
    éĢ¼
    0.06
    uz
    0.05
     on
    0.05
    c
    0.05
    aps
    0.05
    alt
    0.05
    ns
    0.05
    Activations Density 0.019%

    No Known Activations