© 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. 7428
    Prev
    Next
    INDEX
    Explanations

    speed or ease

    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
    缴åĪ°
    -0.12
    çıĬçijļ
    -0.10
    å¤ļå¹´çļĦ
    -0.10
    å¨ĺå¨ĺ
    -0.10
    å»¶è¿Ł
    -0.09
    继ç»Ńä¿ĿæĮģ
    -0.09
    Until
    -0.09
    延误
    -0.09
    å¤ļå¹´
    -0.09
     until
    -0.09
    POSITIVE LOGITS
    æĻ·
    0.10
    ghan
    0.09
    pm
    0.08
    çijľ
    0.08
    /topics
    0.08
     chóng
    0.08
    被æ·ĺæ±°
    0.08
    å°±å¼Ģå§ĭ
    0.08
    åĩºå±Ģ
    0.08
    çĿĢæīĭ
    0.08
    Activations Density 0.224%

    No Known Activations