© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20898
    Prev
    Next
    INDEX
    Explanations

    hip arthroplasty

    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
    ZION
    -0.06
     néc
    -0.06
    zÄĻ
    -0.06
    estina
    -0.06
    åıĸçļĦ
    -0.06
    hyp
    -0.05
    第ä¸Ģ线
    -0.05
    /Documents
    -0.05
    ledged
    -0.05
    ä¸įæĺ¯ä»Ģä¹Ī
    -0.05
    POSITIVE LOGITS
     Pari
    0.06
    é»ijçĻ½
    0.06
    apore
    0.06
     ÑĩеÑĢно
    0.05
     involving
    0.05
    mak
    0.05
    imers
    0.05
    人éģĵ
    0.05
    æµijæµĬ
    0.05
     rev
    0.05
    Activations Density 0.034%

    No Known Activations