© 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. 14378
    Prev
    Next
    INDEX
    Explanations

    building, making, programs

    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
    ä»Ģä¹Īåij¢
    -0.08
    —which
    -0.08
    DefaultValue
    -0.07
    ùn
    -0.07
    _kwargs
    -0.07
    å°Ĩè¿Ļ个
    -0.07
    ÙĪرت
    -0.07
    .):
    -0.07
    éĤ£ä½į
    -0.07
    以ä¸ĬçļĦ
    -0.07
    POSITIVE LOGITS
     vs
    0.08
    çļĦéĩįè¦ģæĢ§åĴĮ
    0.07
    导读
    0.07
     blah
    0.07
    åħ³æ³¨æĪij们
    0.06
    为åķ¥
    0.06
    åĸľæ¬¢çľĭ
    0.06
    æĹłåīį
    0.06
    ä¸ĢèĪ¬ä¸º
    0.06
    ucked
    0.06
    Activations Density 0.008%

    No Known Activations