© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19292
    Prev
    Next
    INDEX
    Explanations

    medication forms and dosage

    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
    witz
    -0.07
    Ø·Ùģ
    -0.06
    rible
    -0.06
     deadliest
    -0.06
    æ¯Ľ
    -0.06
    erma
    -0.06
    desde
    -0.06
     provoc
    -0.06
    angel
    -0.06
    Fold
    -0.06
    POSITIVE LOGITS
     вÑĭп
    0.05
    outs
    0.05
    пиÑģание
    0.05
    è¡
    0.05
    ifica
    0.05
     заÑģед
    0.05
    éĿ¢åŃĶ
    0.05
    ÑĤиÑı
    0.05
    ä¸Ģé¢Ĺ
    0.05
    ëĭĪëĭ¤
    0.05
    Activations Density 0.009%

    No Known Activations