© 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. 60085
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

    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
     جد
    -0.08
    pch
    -0.08
     drastically
    -0.08
    kou
    -0.07
    è®¤çľŁè´¯å½»èIJ½å®ŀ
    -0.07
    å§Ķæ´¾
    -0.07
    ãĥĥãĥģ
    -0.07
    Subset
    -0.07
    ÙĪائ
    -0.07
    dent
    -0.07
    POSITIVE LOGITS
     beyond
    0.11
    è¶ħè¶Ĭ
    0.11
    æī©å¤§
    0.10
    æī©åħħ
    0.10
    æī©å±ķ
    0.09
    -expanded
    0.09
    æī©
    0.09
    è¶ħè¶ĬäºĨ
    0.09
    è¶ħåĩºäºĨ
    0.09
     Beyond
    0.09
    Activations Density 0.124%

    No Known Activations