© 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. 20532
    Prev
    Next
    INDEX
    Explanations

    chemical reactions and products

    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
    emean
    -0.08
     inher
    -0.07
    å¹»
    -0.07
    iak
    -0.07
    天åħĥ
    -0.07
    _SECURITY
    -0.07
    æľī幸
    -0.07
    elai
    -0.06
    æī¿
    -0.06
    åĨħæł¸
    -0.06
    POSITIVE LOGITS
    ç©
    0.09
    空éĹ´åĴĮ
    0.08
     accumulation
    0.08
    ä¸įåĪ©
    0.08
     favorable
    0.08
     favourable
    0.08
     Favor
    0.07
    space
    0.07
    ä¿ĥ使
    0.07
    -space
    0.07
    Activations Density 0.010%

    No Known Activations