© 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. 35766
    Prev
    Next
    INDEX
    Explanations

    virgin mary

    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
    acus
    -0.12
    æŃ»äº¡
    -0.10
    溥
    -0.10
    èĶ»
    -0.09
    çĮ·
    -0.09
    è£ĺ
    -0.09
    åĥ§
    -0.09
    æĭĨ
    -0.09
    æĬĦè¢Ń
    -0.09
    æĢ»éĥ¨
    -0.09
    POSITIVE LOGITS
    åŃķ
    0.10
    å¦ĩ
    0.10
    æ¯į
    0.10
    è·Łå¥¹
    0.10
    夫
    0.09
    æĭĹ
    0.09
    女
    0.09
    ibold
    0.08
    è·ŁæĪij
    0.08
    åŃķèĤ²
    0.08
    Activations Density 0.028%

    No Known Activations