© 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. 17888
    Prev
    Next
    INDEX
    Explanations

    chemistry and related concepts

    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
    审
    -0.07
    伤
    -0.06
    çĹĩ
    -0.06
    åħ¬å¹³
    -0.06
    æ»ĭ
    -0.06
     silently
    -0.06
     yaw
    -0.06
    oded
    -0.06
    æīĢè¦ģ
    -0.06
     anonym
    -0.06
    POSITIVE LOGITS
     versatile
    0.08
    åħ·æľī丰å¯ĮçļĦ
    0.08
     acidic
    0.08
    稳å®ļæĢ§
    0.08
    为æĤ¨ä»ĭç»į
    0.08
     chemistry
    0.08
    ë·Ķ
    0.07
     strongly
    0.07
    æł·æł·
    0.07
    çļĦæĢ§è´¨
    0.07
    Activations Density 0.022%

    No Known Activations