© 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. 22127
    Prev
    Next
    INDEX
    Explanations

    medical or technical contexts

    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
     hailed
    -0.07
    iggs
    -0.07
    om
    -0.06
     coherent
    -0.06
     d
    -0.06
    æĦŁåħ´è¶£çļĦ
    -0.06
     er
    -0.06
    ARP
    -0.06
     Weaver
    -0.06
    arrer
    -0.06
    POSITIVE LOGITS
    nesc
    0.08
    éĥ
    0.08
    åĺī
    0.08
    èĴ
    0.07
    çŀ»
    0.07
    enance
    0.07
    ãģĭãĤĵ
    0.07
    (Font
    0.07
    -loader
    0.07
    колÑĮ
    0.07
    Activations Density 0.312%

    No Known Activations