© 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. 44318
    Prev
    Next
    INDEX
    Explanations

    shell scripts

    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
    Negative Logits
    衬
    -0.07
    bsd
    -0.07
    åħįè´¹é¢Ĩåıĸ
    -0.07
     зама
    -0.07
    ensen
    -0.07
    ambu
    -0.06
     abolished
    -0.06
     formed
    -0.06
    .returnValue
    -0.06
    ä¾Ħ
    -0.06
    POSITIVE LOGITS
    èĦļæľ¬
    0.10
     script
    0.10
     remotely
    0.09
     scripts
    0.09
    æĶ¿æ²»ä»»åĬ¡
    0.08
     Script
    0.08
     staging
    0.08
     run
    0.08
    çĴĢ
    0.08
    .cmd
    0.08
    Activations Density 0.718%

    No Known Activations