© 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. 16645
    Prev
    Next
    INDEX
    Explanations

    search for terms or items

    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
    UnderTest
    -0.09
    æĸ¯çļĦ
    -0.08
    ities
    -0.08
    ently
    -0.08
    çīº
    -0.08
    .heroku
    -0.08
     sano
    -0.08
    ernity
    -0.07
    OnError
    -0.07
    versorgung
    -0.07
    POSITIVE LOGITS
    es
    0.10
    er
    0.10
    eres
    0.09
    lights
    0.09
    able
    0.09
    s
    0.09
    sorted
    0.08
    light
    0.08
    ese
    0.08
    /search
    0.08
    Activations Density 0.060%

    No Known Activations