© 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. 48315
    Prev
    Next
    INDEX
    Explanations

    acidified potassium, precipitation method, alkaline

    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
    åĢŁçĶ¨
    -0.07
     typ
    -0.07
    regular
    -0.07
     figur
    -0.06
    天éķ¿
    -0.06
    å¸Ĥéķ¿
    -0.06
    åIJ®
    -0.06
    Regular
    -0.06
    วิà¹Īà¸ĩ
    -0.06
    Inside
    -0.06
    POSITIVE LOGITS
     конÑĤÑĢоли
    0.08
    å¥ĩèīº
    0.08
    æݧåĪ¶åľ¨
    0.08
    endorf
    0.08
    ardu
    0.08
     arrests
    0.07
     gently
    0.07
    ilton
    0.07
    egas
    0.07
    ilter
    0.07
    Activations Density 0.015%

    No Known Activations