© 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. 20965
    Prev
    Next
    INDEX
    Explanations

    medical conditions and patient status

    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
     pretended
    -0.06
     supposed
    -0.06
     freaking
    -0.06
    ниÑĩ
    -0.06
    éļıå¿ĥæīĢ欲
    -0.06
    ä¸įä¸ĭ
    -0.06
     secret
    -0.06
    iki
    -0.06
     Vent
    -0.06
    dle
    -0.06
    POSITIVE LOGITS
    ÑĨеÑĢ
    0.06
    uzzy
    0.05
    har
    0.05
    agg
    0.05
    åĪģ
    0.05
    éĿ¢æİĪ
    0.05
    çŃĸ
    0.05
    享
    0.05
    elier
    0.05
    äch
    0.05
    Activations Density 0.071%

    No Known Activations