© 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. 60918
    Prev
    Next
    INDEX
    Explanations

    manifold, bundle, scheme

    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
    -0.07
     Phuket
    -0.06
    oo
    -0.06
    æijĨæĶ¾åľ¨
    -0.06
    ãĥ¼ãĤ¿ãĥ¼
    -0.06
     dis
    -0.06
    o
    -0.05
    addy
    -0.05
    asin
    -0.05
    说ä¸įåĩºçļĦ
    -0.05
    POSITIVE LOGITS
    вÑĮÑİ
    0.09
    .subplots
    0.09
    åİ»ä½ķ
    0.09
     cigaret
    0.09
    enhagen
    0.08
     soggi
    0.08
    GenericType
    0.08
    urada
    0.08
     interiors
    0.08
     kautta
    0.08
    Activations Density 0.006%

    No Known Activations