© 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. 52518
    Prev
    Next
    INDEX
    Explanations

    today or afternoon

    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
    é»İæĺİ
    -0.10
    æ¯ıå¹´éĥ½
    -0.10
    ÑģÑĤÑĢ
    -0.09
    å¢ŀéķ¿çİĩ
    -0.09
    umin
    -0.09
    pn
    -0.08
    ÑĢабаÑĤ
    -0.08
    çľ¼ä¸ĭ
    -0.08
    .localization
    -0.08
    UserProfile
    -0.08
    POSITIVE LOGITS
    å½ĵæĹ¥
    0.10
    å½ĵ天
    0.10
    è¿Ļä¸Ģ天
    0.10
     OPTIONAL
    0.09
    åIJİèĢħ
    0.09
     event
    0.09
    è¢ĸ
    0.09
    çī¹åĪ¥
    0.08
    OPTION
    0.08
    witter
    0.08
    Activations Density 0.035%

    No Known Activations