© 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. 11048
    Prev
    Next
    INDEX
    Explanations

    difference between

    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
    èĩªä½ľ
    -0.07
    YN
    -0.07
    äºijå³°
    -0.07
    rade
    -0.07
    untas
    -0.07
    ãģ»ãģĨ
    -0.07
    æľŁè´§å¸Ĥåľº
    -0.06
    aÅŁ
    -0.06
    ä¸īå°º
    -0.06
    alink
    -0.06
    POSITIVE LOGITS
    åĮºåĪ«
    0.13
    对å¾ħ
    0.13
     distinguish
    0.11
    å·®åĪ«
    0.11
    å¾ħéģĩ
    0.11
     distinction
    0.11
     distingu
    0.10
    åĮºåĪ«äºİ
    0.10
    çļĦåĮºåĪ«
    0.10
    å°įå¾ħ
    0.10
    Activations Density 0.130%

    No Known Activations