© 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. 843
    Prev
    Next
    INDEX
    Explanations

    HP Hewlett-Packard Development Company

    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
    Negative Logits
     Ñģамом
    -0.09
    åħ¨åĽ½äººå¤§
    -0.09
    IRD
    -0.09
    .NewReader
    -0.09
    strup
    -0.09
    entai
    -0.09
    æĹĹå¸ľ
    -0.09
    éĺ®
    -0.08
    à¹ĥà¸ļ
    -0.08
     vanity
    -0.08
    POSITIVE LOGITS
    ï¸
    0.11
    олов
    0.10
    ä¸ĢåĪĨéĴŁ
    0.09
    hoot
    0.08
     воÑģ
    0.08
    èĦ¾
    0.08
    pink
    0.08
     Doom
    0.08
    å°Ķ
    0.08
     pública
    0.08
    Activations Density 0.013%

    No Known Activations