© 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. 54645
    Prev
    Next
    INDEX
    Explanations

    retired, earned, member

    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
    èĤ®
    -0.11
    æķĿ
    -0.10
    RESS
    -0.09
    errated
    -0.09
    è¿Ļ群
    -0.09
     (![
    -0.08
    沮丧
    -0.08
    éļĶçĿĢ
    -0.08
    ÅĤe
    -0.08
    é«ĺæ¡£
    -0.08
    POSITIVE LOGITS
    å¤ļ次
    0.08
     faithfully
    0.08
    åħ«åŃĹ
    0.08
    çģ«çĥ§
    0.08
    ä¸Ģ缴éĥ½æĺ¯
    0.07
    æİĴæ¯Ĵ
    0.07
    çĢļ
    0.07
    éģįåıĬ
    0.07
    ä»ĸæĽ¾
    0.07
    ä¸ĢåŃĹ
    0.07
    Activations Density 0.150%

    No Known Activations