© 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. 37114
    Prev
    Next
    INDEX
    Explanations

    Furious, Five, Fighter

    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
    èĮħ
    -0.11
    é«ĺ度
    -0.09
    ä½ľäºĨ
    -0.08
    æł¹æį®èĩªå·±
    -0.08
    etag
    -0.08
    poses
    -0.08
    å±±åºĦ
    -0.08
    åĤ£
    -0.08
    èĬ½
    -0.08
     Majority
    -0.08
    POSITIVE LOGITS
    åĨĮ
    0.10
    æĪIJåIJį
    0.09
    eln
    0.08
    Tpl
    0.08
    TH
    0.08
    ÐŁÐµÑĤеÑĢбÑĥÑĢг
    0.08
    éĿ¡
    0.08
    oko
    0.08
    odes
    0.08
    eer
    0.08
    Activations Density 0.002%

    No Known Activations