© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 47669
    Prev
    Next
    INDEX
    Explanations

    thyroid and related conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reuse
    -0.08
     prostata
    -0.08
    linger
    -0.08
    komm
    -0.08
     dâu
    -0.08
    MSG
    -0.07
    öks
    -0.07
     Pist
    -0.07
    ONY
    -0.07
    åĬłæĭ¿å¤§çļĦ
    -0.07
    POSITIVE LOGITS
    åħ¨å¥Ĺ
    0.07
    erna
    0.07
    ernal
    0.07
    è°ĥèĬĤ
    0.06
     circulating
    0.06
    ern
    0.06
    antar
    0.06
    æľ«
    0.06
    iggins
    0.06
    ectomy
    0.06
    Activations Density 0.043%

    No Known Activations