© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 63758
    Prev
    Next
    INDEX
    Explanations

    version, software, languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .jupiter
    -0.10
    çİ·
    -0.10
    æĿ¥èĩª
    -0.10
    etch
    -0.09
    çĶŁæĢģåľĪ
    -0.09
     yakın
    -0.09
    ä¾Ĩèĩª
    -0.09
    GES
    -0.09
    éķĽ
    -0.08
    縻
    -0.08
    POSITIVE LOGITS
    éĤ£è¾¹
    0.13
     counterparts
    0.11
     version
    0.10
    å±ĤéĿ¢
    0.10
     counterpart
    0.10
     versions
    0.09
    åIJĮè¡Į
    0.08
    çīĪæľ¬
    0.08
    æķ£
    0.08
    -Version
    0.08
    Activations Density 0.339%

    No Known Activations