© 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. 64430
    Prev
    Next
    INDEX
    Explanations

    signed routes, candidate master, atomic absorption

    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
    à·Ķà·Ģ
    -0.07
    estina
    -0.07
    ahl
    -0.07
    çĨĦçģ«
    -0.06
    ãĥģãĥ¥ãĥ¼
    -0.06
    erv
    -0.06
    ä¼ĺçĶŁ
    -0.06
    ä¸Ģç§Ĵ
    -0.06
    вÑĸÑĢ
    -0.06
    sig
    -0.06
    POSITIVE LOGITS
    cene
    0.08
    æĪİ
    0.08
    _CD
    0.07
    lify
    0.07
    mtree
    0.07
    举
    0.07
    临
    0.07
    utters
    0.07
    ä¼IJ
    0.07
    crement
    0.07
    Activations Density 0.163%

    No Known Activations