© 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. 21395
    Prev
    Next
    INDEX
    Explanations

    ultrasound imaging and diagnostics

    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
    åĴ¬çīĻ
    -0.06
    大æĤ²
    -0.06
    åıijä½ľ
    -0.06
    ä¸İåħ±
    -0.06
     spike
    -0.05
    rets
    -0.05
    åĵ¥
    -0.05
    ocol
    -0.05
    åĪ°è¿ĩ
    -0.05
    åĴĮå¤ĦçIJĨ
    -0.05
    POSITIVE LOGITS
    trasound
    0.06
    家常
    0.06
    çħŀ
    0.06
    razil
    0.05
    绩æķĪè¯Ħä»·
    0.05
    estr
    0.05
    导管
    0.05
    agh
    0.05
    ç§ijåѦéĻ¢
    0.05
    åij±åij±
    0.05
    Activations Density 0.047%

    No Known Activations