© 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. 45468
    Prev
    Next
    INDEX
    Explanations

    one or two

    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
    .impl
    -0.07
    å®ŀè´¨
    -0.07
    apis
    -0.07
    avery
    -0.07
    .wr
    -0.07
    çļĦåħ¶ä»ĸ
    -0.06
    ovich
    -0.06
    EQUAL
    -0.06
    ivain
    -0.06
    =W
    -0.06
    POSITIVE LOGITS
    å½±åĵįåĬĽçļĦ
    0.07
    产çĶŁå½±åĵį
    0.07
    orti
    0.07
     бан
    0.06
    å½±éŁ¿åĬĽ
    0.06
    ãģ»ãģ©ãģ®
    0.06
    éĤ£ä¹Īå¤ļçļĦ
    0.06
     noticeably
    0.06
    ãģ»ãģ©
    0.06
    å½±åĵį
    0.06
    Activations Density 0.129%

    No Known Activations