© 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. 36954
    Prev
    Next
    INDEX
    Explanations

    RSS feed

    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
    ä¸įä¸ĭ
    -0.11
    æ¾¥
    -0.10
    неж
    -0.09
    èĭķ
    -0.09
    åĶ±
    -0.08
    妲
    -0.08
    åĪĩå°Ķ
    -0.08
    çľģéĴ±
    -0.08
    èµĦæºIJæķ´åIJĪ
    -0.08
    é»İæĺİ
    -0.08
    POSITIVE LOGITS
    伤
    0.09
    hog
    0.09
    æ»ļæ»ļ
    0.09
    åĴ¬
    0.08
    à¸ļำ
    0.08
    iec
    0.08
    RSS
    0.08
    reas
    0.08
    urai
    0.08
    åĪļæīį
    0.08
    Activations Density 0.034%

    No Known Activations