© 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. 37717
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

    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
    деб
    -0.07
    antro
    -0.06
    tras
    -0.06
    è¿ĺåı¯ä»¥
    -0.06
    antic
    -0.06
    ä½łè¿ĺåı¯ä»¥
    -0.05
    å¯Ħ
    -0.05
    æĹłçĹĩçĬ¶
    -0.05
    ¬ģ
    -0.05
    çĬ¯çļĦ
    -0.05
    POSITIVE LOGITS
    ìĪł
    0.09
    èĤ²
    0.08
    ritch
    0.08
    omatis
    0.08
    å®ļäºİ
    0.08
    aval
    0.08
    سÙĬÙħ
    0.08
    rige
    0.07
    charset
    0.07
    recated
    0.07
    Activations Density 0.001%

    No Known Activations