© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9634
    Prev
    Next
    INDEX
    Explanations

    Babylonian or similar suffixes

    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
    fty
    -0.09
    ÙĥÙĦ
    -0.09
    asley
    -0.09
    æ¡£
    -0.08
    ãģ®ãģĮ
    -0.08
    SingleNode
    -0.08
    ingly
    -0.08
    ÅĤ
    -0.08
    ä¸įçķĻ
    -0.08
    ownt
    -0.08
    POSITIVE LOGITS
    å°¼äºļ
    0.12
    ¶
    0.11
    ../../../
    0.09
    สรร
    0.09
    0.09
    ÂŃi
    0.09
    主ä¹ī
    0.09
    OOT
    0.08
    athan
    0.08
    INE
    0.08
    Activations Density 0.010%

    No Known Activations