© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 12095
    Prev
    Next
    INDEX
    Explanations

    way to want

    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
    ugd
    -0.08
    áĥĺáĥª
    -0.07
    ÙĦÙĪ
    -0.07
    ÐŁÐļ
    -0.07
    羣çĪ±
    -0.07
    å¾Īå¤ļä¸ľè¥¿
    -0.07
    jual
    -0.07
    å¾Īå¤ļåľ°æĸ¹
    -0.07
    posal
    -0.07
    pong
    -0.07
    POSITIVE LOGITS
    æĤĶ
    0.07
    èĥ½ä½¿
    0.07
    orious
    0.07
    ardt
    0.07
    ry
    0.07
     Downing
    0.07
    embe
    0.07
     somehow
    0.06
    imb
    0.06
    æī¾åĩº
    0.06
    Activations Density 0.080%

    No Known Activations