© 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. 6368
    Prev
    Next
    INDEX
    Explanations

    Did you know that

    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
    ocht
    -0.10
    ardash
    -0.09
    ä¸ĢæŶ
    -0.09
    çĶŁäº§ç»ıèIJ¥
    -0.09
    æĭĻ
    -0.08
    Forever
    -0.08
     بÙĦد
    -0.08
    ç¨Ĺ
    -0.08
    太ä¹ħ
    -0.08
    Known
    -0.08
    POSITIVE LOGITS
    åħ¶å®ŀ
    0.12
    ç«
    0.11
    å®Łãģ¯
    0.11
     surprisingly
    0.10
    æĹ©åľ¨
    0.10
    åħ¶å®ŀæĺ¯
    0.10
    åħ¶å¯¦
    0.10
    ä¸įä»ħèĥ½
    0.10
    èĢĮä¸Ķ
    0.10
    æľīå¾Īå¤ļç§į
    0.09
    Activations Density 0.098%

    No Known Activations