© 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. 21828
    Prev
    Next
    INDEX
    Explanations

    chemical groups and compounds

    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
    ForObject
    -0.09
    ToLocal
    -0.08
    GridLayout
    -0.08
    .JSON
    -0.08
    plx
    -0.08
    ÑĢоди
    -0.07
    æł©æł©
    -0.07
    azgo
    -0.07
    骨çģ°
    -0.07
    ipop
    -0.07
    POSITIVE LOGITS
     acidity
    0.07
    éħ¸æĢ§
    0.07
     acidic
    0.07
    éħ¸
    0.07
    乳头
    0.06
     abuses
    0.06
    dao
    0.06
    Ticks
    0.06
    æ¿¡
    0.06
    Enums
    0.06
    Activations Density 0.008%

    No Known Activations