© 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. 21645
    Prev
    Next
    INDEX
    Explanations

    HTML DOCTYPE

    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
    éĢīæĭ
    -0.11
    æľĽçĿĢ
    -0.09
    jam
    -0.09
    çĤľ
    -0.09
    è¦ģåıĬæŶ
    -0.09
    å¤ļä½ĻçļĦ
    -0.08
    anner
    -0.08
     excess
    -0.08
    åĵĤ
    -0.08
    кÑĥÑģ
    -0.08
    POSITIVE LOGITS
    ä¸Ģç¬Ķ
    0.10
    ä¸ĢéĹ´
    0.09
    istant
    0.09
    æģ¨ä¸įå¾Ĺ
    0.09
    ovich
    0.09
    å«Ĥ
    0.09
    ëģĶ
    0.08
    éĢĸ
    0.08
    ç¨ĭ度
    0.08
    ä¹ĭåĬ¿
    0.08
    Activations Density 0.003%

    No Known Activations