© 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. 37228
    Prev
    Next
    INDEX
    Explanations

    copyrights and licenses

    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
    èµ·æĿ¥äºĨ
    -0.08
    baz
    -0.08
     Lo
    -0.08
    饥
    -0.08
    æĦļ
    -0.08
    orb
    -0.07
    æĭĦ
    -0.07
    å¿ħçĦ¶ä¼ļ
    -0.07
    ç¥ģ
    -0.07
     Fet
    -0.07
    POSITIVE LOGITS
    ãĥģãĥ³
    0.10
    undry
    0.09
    ronics
    0.09
    rons
    0.09
     Reign
    0.09
    æĢ§å¼º
    0.08
     Lumia
    0.08
     chứ
    0.08
    éĤº
    0.08
    çķĻä¸ĭ
    0.08
    Activations Density 0.002%

    No Known Activations