© 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. 9249
    Prev
    Next
    INDEX
    Explanations

    science fiction

    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
    åIJİèĢħ
    -0.10
    edImage
    -0.09
    ä¸įåľ¨
    -0.09
    WO
    -0.09
    ständ
    -0.08
    çĶµä¿¡
    -0.08
    è¿Ļæĺ¯ä¸Ģç§į
    -0.08
    aurus
    -0.08
    udes
    -0.08
    izzer
    -0.08
    POSITIVE LOGITS
    ously
    0.09
    ä½ľå®¶
    0.09
    ëĦĪ
    0.09
    SenderId
    0.09
    èµ°å»Ĭ
    0.09
    èķ¤
    0.09
    лÑij
    0.09
    箸
    0.08
    аÑĢи
    0.08
    ARI
    0.08
    Activations Density 0.009%

    No Known Activations