© 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. 53278
    Prev
    Next
    INDEX
    Explanations

    adjectives describing conditions or importance

    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
    ฯ
    -0.11
    æľ¬èº«çļĦ
    -0.09
    ä¸İä¼Ĺä¸įåIJĮ
    -0.09
    oret
    -0.09
    еннаÑı
    -0.09
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.08
    æµĵæµĵçļĦ
    -0.08
     way
    -0.08
    urd
    -0.08
    ière
    -0.08
    POSITIVE LOGITS
     веÑī
    0.09
    ãģªãĤĤãģ®
    0.08
     projects
    0.08
    (dead
    0.08
    纷纷
    0.08
    åıĶåıĶ
    0.08
    ardon
    0.08
    å¸ĤæĶ¿
    0.08
    legen
    0.08
    (bind
    0.08
    Activations Density 0.777%

    No Known Activations