© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61812
    Prev
    Next
    INDEX
    Explanations

    expected, achieved, correct, reached

    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
    Ł
    -0.08
    æī©å±ķèµĦæĸĻ
    -0.08
     gotta
    -0.08
    ä½łä»¬
    -0.07
    egger
    -0.07
    Scoped
    -0.07
    æĦ¿ä½ł
    -0.07
     yours
    -0.07
    GetData
    -0.07
    ä¸ĩå²ģ
    -0.07
    POSITIVE LOGITS
     unavoid
    0.08
     presently
    0.07
     herein
    0.07
    —as
    0.07
     considerably
    0.07
    -global
    0.07
     amongst
    0.07
     “âĢ¦
    0.07
    -feedback
    0.07
     commonplace
    0.07
    Activations Density 0.772%

    No Known Activations