© 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. 646
    Prev
    Next
    INDEX
    Explanations

    emission lines, electron excitation, astronomers announced

    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
     conditioned
    -0.07
    ç»Łè®¡å±Ģ
    -0.07
     fat
    -0.07
    apers
    -0.06
     ÐĿÐIJТÐŀ
    -0.06
    ross
    -0.06
    à¸ĺ
    -0.06
    .scalar
    -0.06
    VML
    -0.06
    åĵģåij³
    -0.06
    POSITIVE LOGITS
    çĤ«
    0.09
    udu
    0.08
     emitted
    0.08
    计ç®Ĺåħ¬å¼ı
    0.07
    管åĨħ
    0.07
    hoto
    0.07
     Johannes
    0.07
    ocket
    0.07
    ียรà¹Į
    0.07
    åŃ£
    0.07
    Activations Density 0.001%

    No Known Activations