© 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. 3465
    Prev
    Next
    INDEX
    Explanations

    our cultural practices

    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
    èĬĻèĵī
    -0.11
    ä¹ŁæĹłæ³ķ
    -0.10
    çŀ©
    -0.10
    ä¹Łä¸įæķ¢
    -0.09
    wan
    -0.09
     RSS
    -0.08
    å¾Īéļ¾
    -0.08
     пÑĢез
    -0.08
    èĥ¸éĥ¨
    -0.08
     Bea
    -0.08
    POSITIVE LOGITS
    éĹ®éĹ®
    0.12
    审è§Ĩ
    0.12
    çİ°çĬ¶
    0.11
    æĺ¯åIJ¦åŃĺåľ¨
    0.10
    æĺ¯åIJ¦æľī
    0.10
    bourg
    0.10
    æĸ¹æĸ¹éĿ¢éĿ¢
    0.10
    忽çķ¥äºĨ
    0.10
    åıįçľģ
    0.09
    çĸı
    0.09
    Activations Density 0.067%

    No Known Activations