© 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. 9946
    Prev
    Next
    INDEX
    Explanations

    From various sources

    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
    æľīæľŁ
    -0.11
    èĩªä»İ
    -0.11
    æľīæĿĥ
    -0.09
    æĹ¢çĦ¶
    -0.09
    åIJİæľŁ
    -0.09
    lsx
    -0.09
    orda
    -0.09
    ТÐĺ
    -0.09
     Faul
    -0.09
     вла
    -0.09
    POSITIVE LOGITS
    åIJĥåĪ°
    0.09
    è¿ĻçĤ¹
    0.09
    è¿Ļä¸ĢçĤ¹
    0.09
    kowski
    0.08
     Govern
    0.08
    ä¸Ģ个å°ıæŶ
    0.08
    éĤ£äºĽ
    0.08
    çīºçī²
    0.08
    _elems
    0.08
    çĶŁçĶŁ
    0.08
    Activations Density 0.030%

    No Known Activations