© 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. 49306
    Prev
    Next
    INDEX
    Explanations

    yes or right confirmations

    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
    ÑĢоди
    -0.08
     thereby
    -0.08
    éĤ£æĺ¯åĽłä¸º
    -0.08
    åĪĻåı¯
    -0.08
    etti
    -0.07
    кÑĤе
    -0.07
    ä»İèĢĮ使
    -0.07
    angk
    -0.07
    è¿Ļæĺ¯åĽłä¸º
    -0.07
    åĪĻä¼ļ
    -0.07
    POSITIVE LOGITS
    ä¸Ģæĸij
    0.08
    forth
    0.07
    parate
    0.07
    (er
    0.07
    èij±èij±
    0.07
    mente
    0.07
    ens
    0.07
    Ùĭ
    0.06
    enj
    0.06
    ense
    0.06
    Activations Density 0.003%

    No Known Activations