© 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. 40849
    Prev
    Next
    INDEX
    Explanations

    charge, electric charge, charge transfer, charge stored

    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
    ï¸İ
    -0.08
    Allem
    -0.08
    wärts
    -0.08
     chances
    -0.07
    ittle
    -0.07
    컬
    -0.07
    uki
    -0.07
    ãģ¡ãĤĥãĤĵãģ®
    -0.07
    bies
    -0.07
    shire
    -0.07
    POSITIVE LOGITS
    acters
    0.09
    less
    0.08
    vole
    0.08
    нок
    0.08
    radient
    0.08
    (ch
    0.08
    rysler
    0.08
    utip
    0.07
    еÑģÑĤвен
    0.07
    åĴĮç»´çĶŁç´ł
    0.07
    Activations Density 0.034%

    No Known Activations