© 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. 51189
    Prev
    Next
    INDEX
    Explanations

    LaTeX math sections

    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
    eno
    -0.08
    è¿ĩ头
    -0.07
     hel
    -0.07
    eenth
    -0.07
    esson
    -0.07
    erness
    -0.07
    ered
    -0.07
    arily
    -0.07
    ãģĦãĤĭ
    -0.07
    dej
    -0.07
    POSITIVE LOGITS
    Ĵ
    0.08
    <|box_end|>
    0.08
    ¨
    0.07
    ciano
    0.07
    жан
    0.07
     sprav
    0.07
    зив
    0.06
    arate
    0.06
     vX
    0.06
    rato
    0.06
    Activations Density 0.027%

    No Known Activations