© 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. 8583
    Prev
    Next
    INDEX
    Explanations

    medical imaging or radioisotopes

    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
    uela
    -0.07
    è¿ĺæıIJä¾Ľ
    -0.07
    ilyn
    -0.06
    itut
    -0.06
    lit
    -0.06
    éĥ½ä¼ļåľ¨
    -0.06
    çĤ¹è¯Ħ
    -0.06
    rede
    -0.06
    uet
    -0.06
    åĪĨ享åĨħ容
    -0.06
    POSITIVE LOGITS
     **.**
    0.08
    omatis
    0.08
     –**
    0.08
    acto
    0.08
    erras
    0.07
    OTP
    0.07
    ä»Ģä¹Īåij¢
    0.07
    èĭĵ
    0.07
    unto
    0.07
    mitt
    0.07
    Activations Density 0.050%

    No Known Activations