© 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. 36762
    Prev
    Next
    INDEX
    Explanations

    know what or how

    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¸įè§ģ
    -0.10
    æĹłéĶ¡
    -0.09
    æ·¡
    -0.09
    èĭĹ
    -0.08
     Lance
    -0.08
     Lev
    -0.08
    typ
    -0.08
    myp
    -0.08
    strap
    -0.08
    buzz
    -0.08
    POSITIVE LOGITS
    èĮ«çĦ¶
    0.13
    该å¦Ĥä½ķ
    0.11
    æIJĶ
    0.10
    ä¸ĭæīĭ
    0.10
    åºĶ对
    0.10
    å¦Ĥä½ķåİ»
    0.10
    æī¾ä¸įåĪ°
    0.10
     direction
    0.09
    åĩºè·¯
    0.09
    åºĶä»ĺ
    0.09
    Activations Density 0.103%

    No Known Activations