© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44804
    Prev
    Next
    INDEX
    Explanations

    mathematical fractions and sums

    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
    æĸ°åįİ
    -0.07
    çļĦçĶµå½±
    -0.06
    åŁºæľ¬åħ»èĢģä¿ĿéĻ©
    -0.06
    å±ħ家éļĶ离
    -0.06
    æĺ¯è¿Ļæł·çļĦ
    -0.06
    è´Ńä¹°åīį
    -0.06
    losure
    -0.06
    ä¸Ģå¤ķ
    -0.06
    åIJ¬çļĦ
    -0.06
    åĨįè§ģ
    -0.06
    POSITIVE LOGITS
    å®ļ
    0.09
    ESC
    0.08
    ezz
    0.08
     Osw
    0.08
    èĴ²
    0.08
     **.**
    0.08
    med
    0.07
    âm
    0.07
    ä»İåīį
    0.07
    OTP
    0.07
    Activations Density 0.004%

    No Known Activations