© 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. 20165
    Prev
    Next
    INDEX
    Explanations

    that's right

    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
    æİīäºĨ
    -0.10
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    -0.09
    æ¯Ķäºļ
    -0.09
    åĬ£
    -0.09
    à¹īา
    -0.09
    lik
    -0.09
    èijµ
    -0.09
    YT
    -0.09
    æºĥ
    -0.08
     WARNING
    -0.08
    POSITIVE LOGITS
    è¡Įäºĭ
    0.09
    dden
    0.09
    没éĶĻ
    0.09
    ãģĦãģ¾ãģĽãĤĵ
    0.08
    çį»
    0.08
    妩
    0.08
     ske
    0.08
    åĭĥåĭĥ
    0.08
    ä¸įåIJ«
    0.08
    çĮ®
    0.08
    Activations Density 0.004%

    No Known Activations