© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 31420
    Prev
    Next
    INDEX
    Explanations

    quantity, volume, units

    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
    éķij
    -0.07
     muta
    -0.07
    æĹłå¾®ä¸įèĩ³
    -0.07
    Ø°
    -0.07
    è¿ĩ客
    -0.07
    èĸªèµĦå¾ħéģĩ
    -0.07
    indah
    -0.07
    å°»
    -0.07
     kest
    -0.07
    æĹłå¤Ħä¸įåľ¨
    -0.07
    POSITIVE LOGITS
     quantity
    0.11
    éĩıçļĦ
    0.11
    quantity
    0.10
    æķ°éĩıçļĦ
    0.10
    éĩı
    0.10
     quantities
    0.09
    æķ°éĩı
    0.09
     Quantity
    0.09
     volume
    0.09
     volumes
    0.09
    Activations Density 0.052%

    No Known Activations