© 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. 16877
    Prev
    Next
    INDEX
    Explanations

    Glen followed by place names

    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
    ç»ıæµİåѦéĻ¢
    -0.06
    atform
    -0.06
    ersiz
    -0.06
    alj
    -0.06
    ÑģÑĥÑĢ
    -0.05
    urple
    -0.05
    mented
    -0.05
    ampoline
    -0.05
    ä¸įå®ļæľŁ
    -0.05
    ansir
    -0.05
    POSITIVE LOGITS
    ãĢħãģ®
    0.06
    rist
    0.06
    yx
    0.06
    (()=>
    0.06
    roat
    0.06
    rench
    0.06
    vedi
    0.06
    ved
    0.05
    ario
    0.05
    others
    0.05
    Activations Density 0.005%

    No Known Activations