© 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. 33596
    Prev
    Next
    INDEX
    Explanations

    .pdf filenames

    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
    åѦåĪ°äºĨå¾Īå¤ļ
    -0.06
    åIJįè¯į
    -0.06
    neau
    -0.06
     depletion
    -0.06
    os
    -0.06
    osi
    -0.06
    á»ij
    -0.06
    _NS
    -0.06
    bert
    -0.06
    ibert
    -0.06
    POSITIVE LOGITS
    _BACKEND
    0.08
    æľĪçĶŁ
    0.08
    åº
    0.07
    åŃļ
    0.07
    liers
    0.07
    èĬ±æŀľ
    0.07
    andom
    0.07
    iros
    0.07
    ãĥĥãĤ¯ãĤ¹
    0.07
    Ø®ÙĨ
    0.07
    Activations Density 0.025%

    No Known Activations