© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 48376
    Prev
    Next
    INDEX
    Explanations

    positive outcomes and improvements

    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
    ç½ijéĢļ
    -0.10
    åºŀ大
    -0.10
    ä¼ļéĢłæĪIJ
    -0.09
    å°½éĩı
    -0.09
    å°±å¤Ł
    -0.09
    对ä¸įèµ·
    -0.09
    å³»
    -0.09
    鸿
    -0.08
    åºŀ大çļĦ
    -0.08
    amy
    -0.08
    POSITIVE LOGITS
    ä¸įåĨį
    0.13
    åĨįä¹Łä¸į
    0.13
    ä¸įåĨįæĺ¯
    0.11
     improved
    0.11
    æĶ¹åĸĦ
    0.11
    æķĪæŀľ
    0.11
    åīįæīĢæľª
    0.11
    çĦķ
    0.11
    æıIJé«ĺäºĨ
    0.10
    åīįæīĢæľªæľī
    0.10
    Activations Density 0.113%

    No Known Activations