© 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. 16104
    Prev
    Next
    INDEX
    Explanations

    single, one, unilateral

    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
    åĽ¢
    -0.08
    .Basic
    -0.07
    uit
    -0.07
    åĽ£
    -0.07
    emodel
    -0.07
    _BL
    -0.07
    ä¸İä¸ĸçķĮ
    -0.06
    åIJ«éĩij
    -0.06
    ç¢Į
    -0.06
    ç§ijçłĶ
    -0.06
    POSITIVE LOGITS
    åįķè¾¹
    0.16
    åįķæĸ¹éĿ¢
    0.15
     alone
    0.13
    åįķæĸ¹
    0.12
     unilateral
    0.12
     seule
    0.12
    åıªæľīä¸Ģ个
    0.12
    /single
    0.11
    çĭ¬è¡Į
    0.11
    çĭ¬
    0.11
    Activations Density 0.058%

    No Known Activations