© 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. 19395
    Prev
    Next
    INDEX
    Explanations

    catalysis and intermediates

    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
    æ±ķ
    -0.08
    åľ³
    -0.08
    ÑģÑĢе
    -0.08
    ä»ĸ表示
    -0.08
    lias
    -0.08
    zl
    -0.08
    éĶIJæĦıè¿Ľåıĸ
    -0.08
    заÑĢ
    -0.07
    agedList
    -0.07
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.07
    POSITIVE LOGITS
    è¢Ħ
    0.08
    init
    0.07
    ope
    0.07
     поÑĪа
    0.07
     entry
    0.06
     Mem
    0.06
    åį¸
    0.06
    æħ¢
    0.06
    -entry
    0.06
    mem
    0.06
    Activations Density 0.004%

    No Known Activations