© 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. 19733
    Prev
    Next
    INDEX
    Explanations

    French or Mandarin education

    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
    åºķ线
    -0.11
    èĥľè´Ł
    -0.09
    Selectable
    -0.09
    åĨ»ç»ĵ
    -0.09
    åĢŁéĴ±
    -0.09
    åIJİæĤĶ
    -0.09
    æį®ç»Łè®¡
    -0.09
    大åѦçĶŁ
    -0.08
    uml
    -0.08
    çĬĴ
    -0.08
    POSITIVE LOGITS
    浸
    0.10
    è¿ľæ´ĭ
    0.09
    éĥ¦
    0.09
    èij£äºĭ
    0.09
    åįĩåѦ
    0.09
    å¼ķ
    0.09
    éªł
    0.09
    转载请
    0.09
    æĬĵ
    0.08
     обÑıз
    0.08
    Activations Density 0.093%

    No Known Activations