© 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. 8835
    Prev
    Next
    INDEX
    Explanations

    German or foreign names/origins

    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
    Tail
    -0.07
    lipp
    -0.07
     Ont
    -0.07
    klus
    -0.06
     Tail
    -0.06
    å¦Ħ
    -0.06
    oretical
    -0.06
    تÙī
    -0.06
    ignano
    -0.06
    iÄħ
    -0.06
    POSITIVE LOGITS
     equivalents
    0.10
     similarly
    0.10
     equivalent
    0.09
     analogous
    0.09
    缸åºĶ
    0.09
    åĴĮæĹ¥æľ¬
    0.09
     counterpart
    0.09
    hing
    0.08
    类似çļĦ
    0.08
     counterparts
    0.08
    Activations Density 0.180%

    No Known Activations