© 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. 55561
    Prev
    Next
    INDEX
    Explanations

    optimization and constraints

    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
    é¾Ļåĩ¤
    -0.07
     Silent
    -0.07
    éļĶ
    -0.07
     kauf
    -0.07
    æµģ
    -0.07
    ickers
    -0.06
    éĢļè¿ĩè¿ĻäºĽ
    -0.06
     silently
    -0.06
     веÑĢоÑıÑĤ
    -0.06
    ayer
    -0.06
    POSITIVE LOGITS
    约æĿŁ
    0.12
     constraint
    0.12
    constraint
    0.11
     maximize
    0.11
     constraints
    0.11
     maximizing
    0.11
    æľĢ大åĮĸ
    0.10
     constrained
    0.10
     optimizing
    0.10
     Constraint
    0.09
    Activations Density 0.004%

    No Known Activations