© 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. 63944
    Prev
    Next
    INDEX
    Explanations

    L- to M-cone

    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
    çĶļèĩ³æ¯Ķ
    -0.07
    NV
    -0.07
    HANDLE
    -0.07
    èµĦæľ¬ä¸»ä¹ī
    -0.07
    æĸĽ
    -0.07
     %#
    -0.07
     famil
    -0.06
    áĢĦáĢº
    -0.06
    é¦ĸåºľ
    -0.06
    nes
    -0.06
    POSITIVE LOGITS
    emus
    0.07
    çľĭåľ¨
    0.07
    dba
    0.07
    æľ
    0.07
    AYER
    0.07
    ç¬ijåĤ²
    0.07
    είο
    0.07
    åijĬ
    0.07
    èĬŃ
    0.06
    avanaugh
    0.06
    Activations Density 0.004%

    No Known Activations