© 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. 58041
    Prev
    Next
    INDEX
    Explanations

    medical terms

    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
    veen
    -0.07
    inally
    -0.07
    .design
    -0.07
    åIJ«çĿĢ
    -0.07
    å²Ń
    -0.07
    orce
    -0.07
    ãĥ¼ãĥĬ
    -0.06
    ULD
    -0.06
    继
    -0.06
    ritch
    -0.06
    POSITIVE LOGITS
    ä¸įå½±åĵį
    0.08
    ButtonText
    0.08
    æĶ¹éĢł
    0.07
     diserta
    0.07
    ToLeft
    0.07
    uchu
    0.07
     modifies
    0.07
     Phill
    0.07
     alters
    0.07
    å½±åĵį
    0.07
    Activations Density 0.398%

    No Known Activations