© 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. 19840
    Prev
    Next
    INDEX
    Explanations

    we hope you find

    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
    å¾ģ
    -0.09
    æīįèĥ½
    -0.09
    éĢ¼
    -0.08
    èĬĤ
    -0.08
    èĩ³åħ³
    -0.08
    åı©
    -0.08
    èĢĮå·²
    -0.08
    顶å±Ĥ
    -0.08
    æĻ®éĢļ人
    -0.08
    æıIJåĢ¡
    -0.08
    POSITIVE LOGITS
     yourselves
    0.12
    满æĦıçļĦ
    0.12
    æĦīå¿«
    0.10
    æľīæīĢ帮åĬ©
    0.10
    æīĢæıIJä¾ĽçļĦ
    0.10
    ä½łä»¬
    0.09
    ä¼ļè§īå¾Ĺ
    0.09
    æĪĸå¤ļæĪĸå°ij
    0.09
    æ¯ĶæĪij
    0.09
    è¿Ļæĺ¯æĪij们
    0.09
    Activations Density 0.051%

    No Known Activations