© 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. 34731
    Prev
    Next
    INDEX
    Explanations

    skipping, streak, tears, message, hold

    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
    éĽĨ
    -0.07
    éģĩåĪ°
    -0.06
    ourse
    -0.06
    пÑĢавлÑı
    -0.06
    kom
    -0.06
    客
    -0.06
    ONES
    -0.06
    äºĮ次
    -0.06
    åĤ¬
    -0.06
    ambi
    -0.06
    POSITIVE LOGITS
     appunto
    0.09
    åĨįè§ģ
    0.08
    abin
    0.08
    othing
    0.08
     Flach
    0.07
    èij©
    0.07
    ãĢĤï¼ī
    0.07
    çī¹åĭĴ
    0.07
    ç¡®
    0.07
    èĩªè¾¾
    0.07
    Activations Density 0.031%

    No Known Activations