© 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. 43905
    Prev
    Next
    INDEX
    Explanations

    bounds for graph coloring

    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
    subs
    -0.08
    æ±ĩåħ¥
    -0.07
    ampa
    -0.07
    ä¸įæĥĬ
    -0.07
     Fres
    -0.06
    æ·±æµħ
    -0.06
    ission
    -0.06
    ikke
    -0.06
    .asc
    -0.06
    åĨ²åĪ·
    -0.06
    POSITIVE LOGITS
    åŁºæķ°
    0.08
    éļıçĿĢå¹´é¾ĦçļĦå¢ŀéķ¿
    0.07
    -margin
    0.07
    eran
    0.07
    ä¸ĭéĻIJ
    0.07
     graph
    0.07
    对åı£
    0.07
     tourn
    0.07
    èĩ
    0.07
    ä»ĭ
    0.07
    Activations Density 0.080%

    No Known Activations