© 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. 38118
    Prev
    Next
    INDEX
    Explanations

    in case of

    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
     Wenger
    -0.10
    çļĦçĹĩçĬ¶
    -0.09
    æ³ķ令
    -0.09
    é»İæĺİ
    -0.08
    çļĦ形象
    -0.08
    è¿Ļ段
    -0.08
    æŶä¸įæŶ
    -0.08
    æıĨ
    -0.08
    æĹ¥æ¶Īæģ¯
    -0.08
    é²ł
    -0.08
    POSITIVE LOGITS
    çĸijéĹ®
    0.10
    avorites
    0.09
     Jad
    0.09
    修为
    0.09
    æī¾ä¸įåĪ°
    0.09
    é£İåIJ¹
    0.08
    ALL
    0.08
    å¹¿æ³Ľ
    0.08
    æĭĻ
    0.08
    ksen
    0.08
    Activations Density 0.031%

    No Known Activations