© 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. 32388
    Prev
    Next
    INDEX
    Explanations

    difference between items

    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
    ä¸įå°ijç½ijåıĭ
    -0.07
    æ¯Ķä¾ĭ
    -0.07
    uds
    -0.07
    ules
    -0.07
    _VOLUME
    -0.07
    ALAR
    -0.07
    æ¯Ķä¾ĭçļĦ
    -0.07
    attet
    -0.07
    uff
    -0.07
    tres
    -0.07
    POSITIVE LOGITS
    ä¹ĭå·®
    0.11
     difference
    0.10
    就差
    0.09
    åıªå·®
    0.09
    çĽ¸å·®
    0.09
    difference
    0.09
     differences
    0.08
     Difference
    0.08
     Differences
    0.08
    æīĢéĢłæĪIJçļĦ
    0.08
    Activations Density 0.042%

    No Known Activations