© 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. 60157
    Prev
    Next
    INDEX
    Explanations

    optimal / maximizing / minimizing

    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
    ardia
    -0.10
    Locker
    -0.08
    uyer
    -0.08
    ERNEL
    -0.07
    ilus
    -0.07
     Montpellier
    -0.07
    .require
    -0.07
    uha
    -0.07
     ë²Į
    -0.07
    ç¯ł
    -0.07
    POSITIVE LOGITS
    å°½åı¯èĥ½
    0.16
     maximizing
    0.15
     optimal
    0.13
     maximize
    0.13
    å°½éĩı
    0.13
    å°½åı¯èĥ½åľ°
    0.13
     maxim
    0.12
     minimizing
    0.12
    å°½éĩıåĩıå°ij
    0.12
    æľĢä¼ĺ
    0.12
    Activations Density 0.010%

    No Known Activations