© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22274
    Prev
    Next
    INDEX
    Explanations

    working to or with

    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
    åıĪèĥ½
    -0.10
    æĢİä¹Īçľĭ
    -0.08
    éĹ®ä»ĸ
    -0.08
     fas
    -0.08
    æīįç®Ĺ
    -0.08
    æµģ失
    -0.08
    ä¸ĢåIJij
    -0.08
    ç»ıèIJ¥æ´»åĬ¨
    -0.08
    æĶ¾åģĩ
    -0.08
    agua
    -0.08
    POSITIVE LOGITS
    æĺİç¡®
    0.10
    _nat
    0.10
    ä¸İåħ¶ä»ĸ
    0.09
    积æŀģ
    0.09
    iani
    0.09
    å°Ĩèĩªå·±çļĦ
    0.09
    ç¡®ä¿Ŀ
    0.08
    ioned
    0.08
    .IsNullOr
    0.08
    ayed
    0.08
    Activations Density 0.031%

    No Known Activations