© 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. 20207
    Prev
    Next
    INDEX
    Explanations

    security, science, health, and biology terms

    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
    åį´æ²¡æľī
    -0.09
    6
    -0.09
    åĩłå®¶
    -0.09
    7
    -0.09
    5
    -0.09
    2
    -0.09
    èijĹ
    -0.08
    неÑĤ
    -0.08
    9
    -0.08
    8
    -0.08
    POSITIVE LOGITS
    æĺ¯æĮĩ
    0.14
    æĺ¯æĪij们
    0.10
    æĺ¯æľĢ
    0.09
    ëŀĢ
    0.09
    Spoiler
    0.09
    æĺ¯ä¸Ģç§į
    0.09
    ãģ¨ãģ¯
    0.09
     [âĢ¦]↵↵
    0.09
    ÑĦи
    0.09
    çĽ¸ä¿¡å¤§å®¶
    0.08
    Activations Density 1.018%

    No Known Activations