© 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. 9920
    Prev
    Next
    INDEX
    Explanations

    Portland

    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
    ãĤĤãģ®
    -0.11
    ën
    -0.10
    ulin
    -0.10
    们
    -0.10
    æĹłå½¢
    -0.10
    åĮ£
    -0.09
    çĮ´
    -0.09
    бин
    -0.09
    åħ¥åħļ
    -0.09
     baÅŁÄ±nda
    -0.09
    POSITIVE LOGITS
    ready
    0.09
    ìį¨
    0.09
    swith
    0.09
    ersen
    0.08
    ista
    0.08
    orman
    0.08
    sson
    0.08
    quist
    0.08
    ä¸įç»ı
    0.08
    åĽłä¸ºä½ł
    0.08
    Activations Density 0.006%

    No Known Activations