© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 9322
    Prev
    Next
    INDEX
    Explanations

    thermodynamics and entropy

    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
    强çĥĪçļĦ
    -0.11
    ä¸Ĭæ¦ľ
    -0.10
    artisan
    -0.09
    å½¼æŃ¤
    -0.09
    éĺħ读åħ¨æĸĩ
    -0.09
    ç¯ĩ
    -0.09
    åī¥ç¦»
    -0.09
    à¹Ģà¸īà¸ŀาะ
    -0.09
    æİĪ
    -0.09
     назнаÑĩен
    -0.09
    POSITIVE LOGITS
     entropy
    0.15
    çĨµ
    0.15
    entropy
    0.14
    Entropy
    0.13
    _entropy
    0.13
     Ent
    0.10
    ä½İ温
    0.09
     therm
    0.09
    èĥ½éĩı
    0.09
     Claus
    0.09
    Activations Density 0.113%

    No Known Activations