© 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. 47375
    Prev
    Next
    INDEX
    Explanations

    reading user input

    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
    urning
    -0.07
    æĹłäºĭ
    -0.07
    eneg
    -0.07
    çĶ¨çģ«
    -0.07
    .pending
    -0.07
    rove
    -0.07
    cox
    -0.07
    èħ¾é£ŀ
    -0.07
    .transforms
    -0.07
    ::$_
    -0.07
    POSITIVE LOGITS
    è¾ĵåħ¥
    0.14
     input
    0.14
     Input
    0.13
    input
    0.13
    /input
    0.11
    Input
    0.11
     inputs
    0.11
    è¾ĵåħ¥çļĦ
    0.11
    =input
    0.11
    -input
    0.11
    Activations Density 0.180%

    No Known Activations