© 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. 15672
    Prev
    Next
    INDEX
    Explanations

    remove element

    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
    enet
    -0.09
     Planet
    -0.07
    ErrorCode
    -0.07
    drig
    -0.07
    åĵ²
    -0.07
    udir
    -0.07
    idl
    -0.07
     Trinh
    -0.07
    å¾Ĺä¸į
    -0.07
    .override
    -0.07
    POSITIVE LOGITS
     оÑĩеÑĢед
    0.07
    移éĻ¤
    0.07
     removal
    0.07
     Removal
    0.07
     Removing
    0.07
    Removing
    0.07
    ä¼ĺåħĪ
    0.07
    é¥
    0.07
    ä¸ĭä¸ĢæŃ¥
    0.07
    ä¸Ģå²ģ
    0.07
    Activations Density 0.025%

    No Known Activations