© 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. 31539
    Prev
    Next
    INDEX
    Explanations

    convertibility and modularity

    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
    aper
    -0.07
    enberg
    -0.06
    åħħåĪĨ认è¯Ĩ
    -0.06
     tend
    -0.06
    olem
    -0.06
    abouts
    -0.06
    adores
    -0.06
    OL
    -0.06
     contr
    -0.06
    oin
    -0.06
    POSITIVE LOGITS
     adaptable
    0.12
     interchangeable
    0.11
    ä¸įåIJĮçļĦ
    0.11
    åĪĩæį¢
    0.10
    æĽ¿æį¢
    0.10
    éĢļçĶ¨
    0.10
    æį¢æĪIJ
    0.10
    éĢĤåºĶ
    0.10
     seamlessly
    0.10
    åıªéľĢ
    0.10
    Activations Density 0.400%

    No Known Activations