© 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. 56312
    Prev
    Next
    INDEX
    Explanations

    as [Name]

    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
     namanya
    -0.08
    è¿Ļ个æĸ¹æ³ķ
    -0.07
    åħ·ä½ĵå¦Ĥä¸ĭ
    -0.07
    对ä»ĺ
    -0.07
    agnostics
    -0.07
    _contents
    -0.07
    iders
    -0.07
    æĢİä¹Īæł·
    -0.07
    ough
    -0.07
    ä¸ĢäºĽéĹ®é¢ĺ
    -0.07
    POSITIVE LOGITS
    âĢ
    0.09
    0.08
    ³³³³
    0.07
    0.07
    ³³³³³³³³
    0.07
    ³³³³³³³
    0.07
    ³³
    0.07
    ubin
    0.06
    ä¹İåħ¶
    0.06
    ;</
    0.06
    Activations Density 0.019%

    No Known Activations