© 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. 11790
    Prev
    Next
    INDEX
    Explanations

    code and text identifiers

    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
     Malone
    -0.07
     Hogan
    -0.07
    ↵
    -0.06
    ارÙĩ
    -0.06
    1
    -0.06
    ä¸įä»ħè¦ģ
    -0.06
    åħ·æľī以ä¸ĭ
    -0.06
     abs
    -0.06
    ä¸įä»ħæľī
    -0.06
    2
    -0.06
    POSITIVE LOGITS
    razi
    0.09
    è§ģ她
    0.08
    æľīéģĵ
    0.08
    åª
    0.08
    éĩĮæĺĤ
    0.08
     ('$
    0.08
    êng
    0.08
     Isab
    0.08
    èĬ±ä¸Ģ
    0.08
    CTOR
    0.08
    Activations Density 0.069%

    No Known Activations