© 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. 36588
    Prev
    Next
    INDEX
    Explanations

    volatile nature

    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
    èĤ¼
    -0.09
    æĶ¹éĢł
    -0.09
    kel
    -0.08
    PA
    -0.08
    paired
    -0.08
    æĶ¹
    -0.08
    æĶ¹å»º
    -0.08
    lift
    -0.08
    ç«Ļåľ¨
    -0.07
    ä¼ĺè¶Ĭ
    -0.07
    POSITIVE LOGITS
    æ³¢åĬ¨
    0.12
    åĬ¨èį¡
    0.11
     volatile
    0.11
    æĿ¥åĽŀ
    0.09
     yüz
    0.09
     vol
    0.09
    éľĩåĬ¨
    0.09
     volatility
    0.09
    éľĩèį¡
    0.09
    èľļ
    0.09
    Activations Density 0.033%

    No Known Activations