© 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. 2756
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables

    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
    è¡£
    -0.07
    ole
    -0.06
    Mur
    -0.06
    æIJIJ
    -0.06
    /react
    -0.06
    jh
    -0.06
     Ear
    -0.06
    yst
    -0.06
    erts
    -0.06
    anel
    -0.06
    POSITIVE LOGITS
    æĶ»
    0.08
    éģĩäºĭ
    0.08
    ãĥĨãĥ¼
    0.08
    нав
    0.08
    à§įদ
    0.08
    itchens
    0.07
     tenden
    0.07
    åIJīåĪ©
    0.07
    æĪ»
    0.07
    -collapse
    0.07
    Activations Density 0.009%

    No Known Activations