© 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. 3678
    Prev
    Next
    INDEX
    Explanations

    accident fiction membership column

    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
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.09
    .removeEventListener
    -0.09
    çļĦç¡®
    -0.08
    ä¸įç»ı
    -0.08
    æŬ
    -0.08
    _soc
    -0.07
     overlooked
    -0.07
    .Typed
    -0.07
    omme
    -0.07
    eni
    -0.07
    POSITIVE LOGITS
    Wh
    0.07
    WT
    0.06
    éĢļè¿ĩåľ¨
    0.06
    åĻ
    0.06
    .LE
    0.06
    ucs
    0.06
    zit
    0.06
    åŃ¦ä¹łåĨħ容
    0.06
    XD
    0.06
    wt
    0.06
    Activations Density 0.678%

    No Known Activations