© 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. 56754
    Prev
    Next
    INDEX
    Explanations

    only one

    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
    ï¸İ
    -0.10
    ül
    -0.09
    lesa
    -0.08
    artment
    -0.08
    ìį¨
    -0.08
    nip
    -0.08
    zie
    -0.08
    isan
    -0.08
    éné
    -0.08
    areth
    -0.08
    POSITIVE LOGITS
    è¿Ļæł·æīįèĥ½
    0.09
    cribe
    0.07
    人
    0.07
    ettings
    0.07
    æĪijä¸Ģ个人
    0.07
    keit
    0.07
    ÙĬ
    0.07
    人èĥ½
    0.07
    à¯į
    0.07
    人åıĹ伤
    0.07
    Activations Density 0.002%

    No Known Activations