© 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. 29297
    Prev
    Next
    INDEX
    Explanations

    therein, circuit, scene

    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
    auer
    -0.07
    .degree
    -0.06
    arp
    -0.06
    ↵    ↵↵
    -0.06
    iep
    -0.06
    vp
    -0.06
    ussin
    -0.06
    pa
    -0.06
    ram
    -0.06
    ade
    -0.06
    POSITIVE LOGITS
    æĩ¿
    0.08
    eref
    0.07
    æĬ¤æ³ķ
    0.07
    çļĦè¿ĻäºĽ
    0.07
    hsi
    0.07
    人çļĦçĶŁæ´»
    0.07
    æĬ¥åijĬä¼ļ
    0.07
    oter
    0.07
    ahas
    0.07
    bane
    0.07
    Activations Density 0.031%

    No Known Activations