© 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. 64313
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    AccessType
    -0.10
    velt
    -0.10
    новиÑĩ
    -0.10
    ãĥĹãĥĪ
    -0.10
    FLAGS
    -0.09
    ecam
    -0.09
    _voice
    -0.09
    ertools
    -0.09
    eyJ
    -0.09
    .getLog
    -0.09
    POSITIVE LOGITS
     -
    0.08
    0.07
    b
    0.07
    c
    0.07
    a
    0.07
    å°ĸ
    0.06
    ?
    0.06
    æŶ
    0.06
    -
    0.06
    çļĦæŶåĢĻ
    0.06
    Activations Density 0.060%

    No Known Activations