© 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. 51612
    Prev
    Next
    INDEX
    Explanations

    over time

    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
    ç»İ
    -0.10
    æŃ£åľ¨è¿Ľè¡Į
    -0.09
    æīĵå¾Ĺ
    -0.09
    åĽ¢
    -0.09
    æĻ¾
    -0.09
    æĻ®éĢļçļĦ
    -0.08
    å°Ĩ以
    -0.08
    æģIJ
    -0.08
    éķ¿æķĪæľºåĪ¶
    -0.08
    çĽ´è¾¾
    -0.08
    POSITIVE LOGITS
    å²ģæľĪ
    0.14
    æŶåħī
    0.13
     years
    0.12
     вÑĢемени
    0.11
    æŶéĹ´åĴĮ
    0.11
    åħīéĺ´
    0.11
     time
    0.11
     ages
    0.10
    沧æ¡ij
    0.10
    ä¸Ģéģĵ
    0.10
    Activations Density 0.057%

    No Known Activations