© 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. 35684
    Prev
    Next
    INDEX
    Explanations

    with | has + feature

    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
    èĥľ
    -0.09
    çĭłçĭł
    -0.09
    çĹ´
    -0.09
    顺åºĶ
    -0.09
    çĮĽåľ°
    -0.09
    OOT
    -0.09
    æľīæĦıä¹ī
    -0.09
    ä¹ı
    -0.08
    ergus
    -0.08
    obot
    -0.08
    POSITIVE LOGITS
    çį¨ç«ĭ
    0.08
    éĩijå±ŀ
    0.08
    éĵº
    0.08
    辦æ³ķ
    0.08
    çİ»çĴĥ
    0.08
    çĴł
    0.08
    åIJĪèµĦ
    0.08
    PropertyDescriptor
    0.08
    çIJī
    0.08
    æĬĺåıł
    0.08
    Activations Density 0.055%

    No Known Activations