© 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. 52155
    Prev
    Next
    INDEX
    Explanations

    temperature and storage conditions

    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
    åĨįä¹Łä¸į
    -0.10
    åĨįä¹Ł
    -0.10
     Tip
    -0.10
    Tip
    -0.10
    æĭ¥æĬ¤
    -0.09
    åĨįä¹Łæ²¡æľī
    -0.09
    æĥij
    -0.09
    æĿ¥æºIJäºİ
    -0.09
    åĩºèĩª
    -0.09
    å¨ĥ
    -0.09
    POSITIVE LOGITS
    éĺ³åħī
    0.14
    antro
    0.11
    çĤ¼
    0.10
    è¾¾æłĩ
    0.10
    纲
    0.10
    storage
    0.09
    structions
    0.09
    ноÑģ
    0.09
     Storage
    0.09
    æľĿéĺ³
    0.09
    Activations Density 0.030%

    No Known Activations