© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8480
    Prev
    Next
    INDEX
    Explanations

    thank you for your help

    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
    æĺı
    -0.11
    åĬŀæ³ķ
    -0.11
    ç´ł
    -0.10
    çļĦåĬŀæ³ķ
    -0.10
    æĪª
    -0.09
    pic
    -0.09
    cro
    -0.09
    欢ä¹IJ
    -0.09
    å°§
    -0.09
    æĹ¦
    -0.09
    POSITIVE LOGITS
     sake
    0.08
    è¿ĻäºĽå¹´
    0.08
    ä»»ä½ķæĹ¶åĢĻ
    0.08
    istle
    0.08
     vel
    0.08
    èĬĴ
    0.08
    äºĭä¸ļéĥ¨
    0.08
    irts
    0.07
    èŀį
    0.07
    DED
    0.07
    Activations Density 0.022%

    No Known Activations