© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10719
    Prev
    Next
    INDEX
    Explanations

    month names and dates

    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
    çĬĩ
    -0.09
    æĥ¯
    -0.09
    ä¸į好
    -0.09
    çŁ¥å·±
    -0.08
    åѦéĹ®
    -0.08
    /or
    -0.08
    æĿ¥åĽŀ
    -0.08
     dereg
    -0.08
    çļ¤
    -0.08
    æĩĴ
    -0.08
    POSITIVE LOGITS
    borg
    0.10
    åĨķ
    0.10
    人åıĤ
    0.10
    ials
    0.09
    æĸ½
    0.09
    .Kind
    0.09
    è¿Ļ件
    0.09
    楼主
    0.09
    roit
    0.09
    rts
    0.09
    Activations Density 0.064%

    No Known Activations