Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 30-TRANSCODER-HP
    4. 15214
    Prev
    Next
    INDEX
    Explanations

    kidney/renal related conditions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    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
    è¢ĭ
    -0.28
    æĵģ
    -0.26
    pta
    -0.26
    è´Ŀ壳
    -0.25
     served
    -0.25
     expelled
    -0.25
     controller
    -0.24
     cul
    -0.24
    .ul
    -0.24
    åī§
    -0.24
    POSITIVE LOGITS
    OND
    0.27
    æ®ĸæ°ij
    0.26
    arness
    0.26
    rina
    0.25
    processors
    0.24
    ritis
    0.24
    rado
    0.24
    inesis
    0.24
    smith
    0.23
    izophren
    0.23
    Activations Density 0.009%

    No Known Activations