© 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. 47981
    Prev
    Next
    INDEX
    Explanations

    infinite loop

    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
    麹
    -0.09
     biá»ĩt
    -0.08
    ä¸½å¨ľ
    -0.08
     scom
    -0.08
    -shared
    -0.08
    addock
    -0.08
    äºĨçĦ¶
    -0.08
    alian
    -0.08
    DTV
    -0.07
    vam
    -0.07
    POSITIVE LOGITS
     infinite
    0.14
    æĹłéĻIJ
    0.13
     indefinite
    0.12
     indefinitely
    0.12
     Infinite
    0.12
     endless
    0.12
    æĹłéĻIJçļĦ
    0.11
     endlessly
    0.11
    æĹłæŃ¢
    0.10
     perpetual
    0.10
    Activations Density 0.047%

    No Known Activations