© 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. 32720
    Prev
    Next
    INDEX
    Explanations

    boolean true/false assignments

    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
    ipot
    -0.08
    קר
    -0.08
    ãģªãģį
    -0.07
    سÙģ
    -0.07
     pore
    -0.07
    à¸Ķีà¹Ĩ
    -0.07
    tribution
    -0.07
    enaar
    -0.07
    uur
    -0.07
    æĹłå½¢
    -0.07
    POSITIVE LOGITS
     false
    0.11
     flag
    0.11
    =false
    0.10
    .bool
    0.10
    false
    0.10
     bool
    0.10
    False
    0.10
    _false
    0.10
     true
    0.09
    -flag
    0.09
    Activations Density 0.152%

    No Known Activations