© 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. 51703
    Prev
    Next
    INDEX
    Explanations

    who

    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
    çľĭä¸Ģçľĭ
    -0.11
     Bounty
    -0.08
    è£ħå¤ĩåĪ¶éĢł
    -0.08
    æĪĸå¤ļæĪĸå°ij
    -0.08
    _MSK
    -0.08
    çĽĨåľ°
    -0.08
     ÐŁÐ¾Ñĩ
    -0.08
    æĿĥåĪ©
    -0.08
    PropertyDescriptor
    -0.08
    纶
    -0.08
    POSITIVE LOGITS
    æĺ¨
    0.09
    ä¸Ĭåij¨
    0.08
     famously
    0.08
    AUT
    0.08
    çĴŀ
    0.08
    -custom
    0.08
    å¤ķ
    0.08
    èĥĮä¸Ĭ
    0.08
    çµ®
    0.08
    ä¸Ĭ次
    0.08
    Activations Density 0.136%

    No Known Activations