© 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. 33219
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and functions

    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
    éģIJ
    -0.07
     sizes
    -0.07
    éĹ
    -0.07
    ulk
    -0.07
    ipper
    -0.06
    tourn
    -0.06
    æµ·
    -0.06
     tourn
    -0.06
    ½Ķ
    -0.06
    ouch
    -0.06
    POSITIVE LOGITS
    èĤ²æīį
    0.08
    æħ
    0.07
    ç·ļçļĦ
    0.07
    æĸĩåįļ
    0.07
     slope
    0.07
     LÃŃ
    0.07
     lobby
    0.07
    å®£ä¼łè´¯å½»
    0.07
    ezo
    0.07
    éĢŀ
    0.07
    Activations Density 0.006%

    No Known Activations