© 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. 17439
    Prev
    Next
    INDEX
    Explanations

    mathematical operators and variables

    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
    ighton
    -0.07
    quita
    -0.07
     Union
    -0.07
    Union
    -0.06
     Bur
    -0.06
     unf
    -0.06
    åĢĶ强
    -0.06
    StateException
    -0.06
    ogna
    -0.06
    å¥ĶåIJij
    -0.06
    POSITIVE LOGITS
     tác
    0.09
     Zut
    0.09
     ACTION
    0.08
    loyd
    0.08
    çĦ¦çħ¤
    0.08
     action
    0.08
     actions
    0.08
    ehme
    0.08
    è¨Ĺ
    0.08
    çļĦä½ľçĶ¨ä¸ĭ
    0.08
    Activations Density 0.007%

    No Known Activations