© 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. 20379
    Prev
    Next
    INDEX
    Explanations

    ranks and degrees

    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
    umon
    -0.09
    arov
    -0.08
    anea
    -0.08
    åĴĮ社ä¼ļåıijå±ķ
    -0.08
    é«ĺéĩĩ
    -0.08
    å¼Ħå¾Ĺ
    -0.08
    ongen
    -0.07
    污
    -0.07
     ÙĪعÙĨ
    -0.07
    æĹłæ±¡æŁĵ
    -0.07
    POSITIVE LOGITS
    åıĬ以ä¸ĭ
    0.14
    -level
    0.13
    åıĬ以ä¸Ĭ
    0.13
     level
    0.13
    级
    0.12
    级åĪ«çļĦ
    0.12
    æĪĸ以ä¸Ĭ
    0.12
    级åĪ«
    0.11
    ä¹ĥèĩ³
    0.11
     voire
    0.11
    Activations Density 0.319%

    No Known Activations