© 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. 57687
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    bled
    -0.09
    bru
    -0.09
    两åı¥
    -0.08
    usan
    -0.08
    æĪIJçĨŁçļĦ
    -0.08
    ÅŁtir
    -0.08
    æѤå¤Ħ
    -0.08
    éĢĤ
    -0.08
     Newark
    -0.08
    æĭİ
    -0.08
    POSITIVE LOGITS
    æĹ¶ä»£çļĦ
    0.10
    _generated
    0.09
    æĿ¥ä¸´
    0.08
    ä¸ĸçķĮ第ä¸Ģ
    0.08
    ewire
    0.08
    inality
    0.08
    ignite
    0.08
    å®īåħ¨éļIJæĤ£
    0.08
    涯
    0.08
    ŀ
    0.08
    Activations Density 0.000%

    No Known Activations