© 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. 10020
    Prev
    Next
    INDEX
    Explanations

    Al followed by words like alumni, albeit, alman, etc

    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
    ĺìĿ´
    -0.10
    ç´ł
    -0.09
    science
    -0.09
    werk
    -0.08
    ëĤľ
    -0.08
    кÑĢ
    -0.08
    èĩ¨
    -0.08
    ologie
    -0.08
    临
    -0.08
     اÙĦÙĪ
    -0.08
    POSITIVE LOGITS
    社ä¼ļ责任
    0.11
    å·²ä¹ħ
    0.10
    çĭĻ
    0.10
    å·²ä¹ħçļĦ
    0.10
    å¹´æĬ¥
    0.09
    è¿ĺæľīä¸ĢäºĽ
    0.09
    å¦ĤæѤ
    0.09
     al
    0.09
    大äºĭ
    0.08
     Loc
    0.08
    Activations Density 0.025%

    No Known Activations