© 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. 14672
    Prev
    Next
    INDEX
    Explanations

    living area. for. period. heat. chipset. layer

    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
    ivy
    -0.08
    enius
    -0.07
    笹
    -0.07
     pac
    -0.07
    液ä¸Ń
    -0.07
    _unused
    -0.07
    躬
    -0.06
    ami
    -0.06
     xá»ī
    -0.06
    żli
    -0.06
    POSITIVE LOGITS
    æĶ¯
    0.10
    è°ĭ
    0.07
    ARTA
    0.07
     journ
    0.07
    å¾
    0.07
    ////////////////////////////////////////////////////////////////////////////
    0.07
    辺
    0.07
     doubl
    0.07
    é¢ĨåħĪ
    0.07
    èĢ
    0.07
    Activations Density 0.040%

    No Known Activations