© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15860
    Prev
    Next
    INDEX
    Explanations

    .fetchall()

    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
    é¢IJ
    -0.07
     })(
    -0.07
    rot
    -0.06
     downs
    -0.06
    رسÛĮ
    -0.06
    /../
    -0.06
    odie
    -0.06
    chor
    -0.06
     figur
    -0.06
    é©¾é©¶æľºåĬ¨è½¦
    -0.06
    POSITIVE LOGITS
    hort
    0.08
    çļĦäºĭäºĨ
    0.07
    essar
    0.07
     Ùħص
    0.07
    occas
    0.07
    artal
    0.07
    payer
    0.07
    _adjust
    0.07
    åħ¶äºĭ
    0.07
    ä¼ĹåĪĽ
    0.07
    Activations Density 0.035%

    No Known Activations