© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2520
    Prev
    Next
    INDEX
    Explanations

    mathematical constraints and inequalities

    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
    Ratio
    -0.08
    æ°´ä¸ŃçļĦ
    -0.07
    rial
    -0.07
    çĤ¼æ²¹
    -0.07
     Mass
    -0.07
     mass
    -0.07
    ratio
    -0.07
     маÑģÑģ
    -0.07
    quat
    -0.07
     Ratio
    -0.07
    POSITIVE LOGITS
    Constraints
    0.09
    åIJĦåĮº
    0.09
    ë¹Ī
    0.09
    约æĿŁ
    0.08
    è¦ģæ±ĤåIJĦ
    0.08
     constraints
    0.08
    counts
    0.08
     Constraints
    0.08
    åĪĨéħįçļĦ
    0.08
     integer
    0.08
    Activations Density 0.004%

    No Known Activations