© 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. 59979
    Prev
    Next
    INDEX
    Explanations

    maps and images

    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
    -
    -0.06
    åĽºæľīçļĦ
    -0.06
    ock
    -0.06
    ill
    -0.06
    åħ¶èº«
    -0.06
    reiber
    -0.06
    ÑģÑĤÑĥп
    -0.06
    åĨħåľ¨
    -0.06
    .inline
    -0.05
    çģµ
    -0.05
    POSITIVE LOGITS
    lesi
    0.09
    è¾Ļ
    0.08
    afen
    0.08
    baut
    0.08
    Ùĥات
    0.08
    éĩĩ访æŶ
    0.08
    ä¹IJ天
    0.08
    /original
    0.07
    ÙħاÛĮÛĮ
    0.07
    çIJ¥
    0.07
    Activations Density 0.004%

    No Known Activations