© 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. 46330
    Prev
    Next
    INDEX
    Explanations

    code initialization and calls

    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
    zg
    -0.07
    inks
    -0.07
    zzi
    -0.07
    ÑĢÑį
    -0.06
    ç²Ĵ
    -0.06
    ä¸įåıĬ
    -0.06
    éĻĮçĶŁ
    -0.06
    =len
    -0.06
    ä»Ģä¹Īéĥ½ä¸į
    -0.06
     Orient
    -0.06
    POSITIVE LOGITS
    Sen
    0.07
    æ³ķ
    0.07
    ĥģ
    0.07
    plist
    0.07
     Stern
    0.06
    夷
    0.06
    åIJĮä¸Ģ
    0.06
    å»
    0.06
    ç¿Ĵ
    0.06
    å©Ĩ
    0.06
    Activations Density 0.038%

    No Known Activations