© 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. 10093
    Prev
    Next
    INDEX
    Explanations

    questions about extensions and exceptions

    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
     calculated
    -0.08
     pellets
    -0.07
     allocated
    -0.07
    è¿Ń
    -0.07
     assigned
    -0.07
    ynet
    -0.07
     intercepted
    -0.06
    ë°°
    -0.06
     Eisenhower
    -0.06
     overl
    -0.06
    POSITIVE LOGITS
    æĶ¾å®½
    0.08
     conject
    0.08
     folklore
    0.08
     weaker
    0.08
    æĹłåıį
    0.07
     extensions
    0.07
    extend
    0.07
     exceptions
    0.07
     restricting
    0.07
    umuman
    0.07
    Activations Density 0.065%

    No Known Activations