© 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. 56949
    Prev
    Next
    INDEX
    Explanations

    periodic phenomena, call centers, same thing

    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
    Remote
    -0.07
     lunches
    -0.07
     Medieval
    -0.07
    æ³ī
    -0.07
    igar
    -0.07
    gup
    -0.07
    лав
    -0.07
    _remote
    -0.07
    udeau
    -0.07
     STRUCT
    -0.07
    POSITIVE LOGITS
    åĮħåİ¢
    0.07
     sin
    0.07
    night
    0.07
    ä¸Ńç«ĭ
    0.07
    ibe
    0.07
    seek
    0.07
     upbeat
    0.07
     Nort
    0.07
    rog
    0.07
    ä¸ĢæĿij
    0.07
    Activations Density 0.002%

    No Known Activations