© 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. 25706
    Prev
    Next
    INDEX
    Explanations

    code delimiters

    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
    åľ¨åĪ«äºº
    -0.08
    Äįer
    -0.08
    ulier
    -0.08
    edig
    -0.08
    lingen
    -0.08
    åħµ
    -0.07
    CORD
    -0.07
    efore
    -0.07
    jek
    -0.07
    lát
    -0.07
    POSITIVE LOGITS
    ous
    0.06
    anske
    0.06
    éĵŃ
    0.06
    aine
    0.06
    åĬłè½½ä¸Ń
    0.06
    éĽ
    0.06
    v
    0.06
    åĴĮèī¯å¥½çļĦ
    0.06
    æĢĿ
    0.05
     pel
    0.05
    Activations Density 0.244%

    No Known Activations