© 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. 19054
    Prev
    Next
    INDEX
    Explanations

    once upon a time

    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
    THON
    -0.09
    çļĦ带é¢Ĩ
    -0.09
    çŁ¿çī©
    -0.09
    è¿ĻçĤ¹
    -0.09
    å¿įä¸įä½ı
    -0.09
    inh
    -0.08
    æľīå¾ħ
    -0.08
    éĽªå±±
    -0.08
    é¼ł
    -0.08
    举
    -0.08
    POSITIVE LOGITS
    æĺĶ
    0.17
    æĽ¾ç»ı
    0.14
    è¿ĩåİ»
    0.14
    æĽ¾
    0.13
    å¤ļå¹´åīį
    0.12
    æĹ¶æľŁçļĦ
    0.12
     ago
    0.12
    éĤ£æŶåĢĻ
    0.12
    æĺĶæĹ¥
    0.12
    ä¹ŁæĽ¾
    0.11
    Activations Density 0.040%

    No Known Activations