© 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. 1697
    Prev
    Next
    INDEX
    Explanations

    bounds and theorems

    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
    zeb
    -0.07
    дено
    -0.07
     ironic
    -0.07
    ä¸ĥä¸ĥ
    -0.07
    å¹´æľŁ
    -0.07
    çĽĬçĶŁ
    -0.07
    CanBe
    -0.07
    ovic
    -0.07
    ikin
    -0.07
    _interest
    -0.06
    POSITIVE LOGITS
    å®ļçIJĨ
    0.07
    /release
    0.07
     unpublished
    0.07
    beda
    0.07
    就差
    0.07
     generalized
    0.07
    é£İå°ĺ
    0.07
    agt
    0.07
    ä½łåİ»
    0.07
     Satz
    0.07
    Activations Density 0.038%

    No Known Activations