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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21035
    Prev
    Next
    INDEX
    Explanations

    extreme temperatures

    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¡åŃIJ
    -0.09
    ä¸ĢåĪĢ
    -0.09
    åıij声
    -0.09
    å¾Ĺ太
    -0.09
    æĥħ绪
    -0.09
    lever
    -0.09
    consts
    -0.09
    æĪij说
    -0.09
    åįłåľ°
    -0.09
    åħįç¨İ
    -0.08
    POSITIVE LOGITS
    é«ĺ温
    0.12
    æŀģ端
    0.11
    éĹ·
    0.11
    麻çĹ¹
    0.10
    Extreme
    0.10
     extreme
    0.10
    emento
    0.10
     extremes
    0.09
    ä¿Ŀåģ¥
    0.09
    chalk
    0.09
    Activations Density 0.147%

    No Known Activations