© 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. 14760
    Prev
    Next
    INDEX
    Explanations

    "I'm", "it looks", "an MP"

    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
    éĹ´éļĶ
    -0.07
    å£Ĭ
    -0.07
    æĥŁä¸Ģ
    -0.07
    irá
    -0.06
    ivate
    -0.06
     Bro
    -0.06
    éĿŀå¿ħè¦ģ
    -0.06
    sent
    -0.06
    usen
    -0.06
     >/
    -0.06
    POSITIVE LOGITS
    è¿ľäºĨ
    0.07
    доÑĤо
    0.07
    ernote
    0.07
    ä¸Ģç²Ĵ
    0.07
    .mul
    0.07
    ÃŃn
    0.06
    angelo
    0.06
    tova
    0.06
    å°ĶçļĦ
    0.06
    ابع
    0.06
    Activations Density 0.001%

    No Known Activations