© 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. 32179
    Prev
    Next
    INDEX
    Explanations

    parts of surfaces or sides

    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
    weiler
    -0.07
    åijµ
    -0.07
    åĨħéĥ¨çļĦ
    -0.07
    uden
    -0.07
    .Dial
    -0.07
    igu
    -0.07
     Insets
    -0.07
    çĤľ
    -0.07
     ÑĢазлиÑĩного
    -0.06
    ä¸įå¾Ĺä»İäºĭ
    -0.06
    POSITIVE LOGITS
    avia
    0.08
    θοÏĤ
    0.08
    andy
    0.07
    èĢĮä¸įæĺ¯
    0.07
    ìa
    0.07
    rather
    0.07
    IDA
    0.07
    è¿ijå¹³
    0.07
    éļĽ
    0.07
    inste
    0.07
    Activations Density 0.196%

    No Known Activations