© 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. 63219
    Prev
    Next
    INDEX
    Explanations

    finish date or strong

    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
     Certa
    -0.09
    ../../../
    -0.09
    ../../../../
    -0.08
    jero
    -0.08
    æŃ¤èµ·
    -0.08
    _initializer
    -0.08
    زش
    -0.08
    вÑĸй
    -0.08
    emény
    -0.08
    åİī害äºĨ
    -0.08
    POSITIVE LOGITS
     xuôi
    0.09
    orses
    0.08
    ter
    0.08
    urance
    0.07
    es
    0.07
    orse
    0.07
    ราà¸Ĭà¸ģาร
    0.07
    /end
    0.07
    urez
    0.07
    ar
    0.06
    Activations Density 0.022%

    No Known Activations