© 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. 50627
    Prev
    Next
    INDEX
    Explanations

    good experience descriptions

    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
    alic
    -0.08
    çĿĽ
    -0.08
    é©°
    -0.08
     заÑĤ
    -0.08
    æµģ浪
    -0.08
    éıĸ
    -0.08
     Stir
    -0.08
     Pic
    -0.08
    è¾ĥ大çļĦ
    -0.08
     stir
    -0.08
    POSITIVE LOGITS
    å·¥ä½ľäººåijĺ
    0.12
     staff
    0.12
    åĸĦèī¯
    0.11
    åıĭåĸĦ
    0.10
    æľįåĬ¡è´¨éĩı
    0.10
    ãĤ¹ãĤ¿ãĥĥãĥķ
    0.10
    çĥŃå¿ĥ
    0.10
    人åijĺ
    0.10
    示æĦı
    0.09
     обÑģлÑĥжива
    0.09
    Activations Density 0.029%

    No Known Activations