© 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. 27933
    Prev
    Next
    INDEX
    Explanations

    possible to

    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
    edly
    -0.10
    allah
    -0.09
    sgi
    -0.08
     Dalle
    -0.08
    å¤ļãģĦ
    -0.08
    วัล
    -0.08
    elian
    -0.08
    ÙĪارد
    -0.08
    edd
    -0.08
    åħ±åĴĮåĽ½
    -0.08
    POSITIVE LOGITS
    iable
    0.09
    o
    0.09
    iment
    0.08
    ibly
    0.08
    ãģĦãģªãģĦ
    0.07
    ayout
    0.07
    mente
    0.07
    ibilities
    0.07
    ibil
    0.07
    -looking
    0.07
    Activations Density 0.039%

    No Known Activations