© 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. 22612
    Prev
    Next
    INDEX
    Explanations

    umbrella or roof rail

    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
    çIJ¢
    -0.10
    èģļçĦ¦
    -0.09
    乡
    -0.09
    åĪĩåħ¥
    -0.09
    kdir
    -0.09
    æºIJæºIJ
    -0.09
     bÃłn
    -0.08
     Jama
    -0.08
    Specifier
    -0.08
    isce
    -0.08
    POSITIVE LOGITS
    大æ£ļ
    0.14
    å¸IJ篷
    0.12
    篷
    0.11
    æ£ļ
    0.10
    rop
    0.10
    温室
    0.09
    å¹Ķ
    0.09
     overst
    0.09
    æ²®
    0.09
    ç¼ĵåĨ²
    0.09
    Activations Density 0.141%

    No Known Activations