© 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. 17966
    Prev
    Next
    INDEX
    Explanations

    medical conditions and specific research subjects

    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
    èĪį
    -0.07
    æĪı
    -0.07
    ê°ĢëĬĶ
    -0.07
    ustos
    -0.06
    parte
    -0.06
    æį¨
    -0.06
    è
    -0.06
     ];
    -0.06
    krank
    -0.06
    è¨Ĺ
    -0.06
    POSITIVE LOGITS
    åłµ
    0.05
    çı
    0.05
     lore
    0.05
     tim
    0.05
    é¸Łå·¢
    0.05
     Nom
    0.05
    te
    0.05
    bes
    0.05
    oli
    0.05
     подÑĢÑıд
    0.04
    Activations Density 0.024%

    No Known Activations