© 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. 19767
    Prev
    Next
    INDEX
    Explanations

    Argentina, Buenos Aires

    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
    æħİ
    -0.10
    棵
    -0.10
    å¥ĭæĸĹ缮æłĩ
    -0.10
    åĩłçĤ¹
    -0.09
    åĪĨå¼Ģ
    -0.09
    _MULT
    -0.09
    æłĩæĺİ
    -0.09
     Pond
    -0.09
    ordan
    -0.08
    æ½Ń
    -0.08
    POSITIVE LOGITS
     Buenos
    0.09
    éĺ¿æł¹å»·
    0.09
    åij½
    0.09
    æĬĵ
    0.08
    ä¸ĵä¸ļåĮĸ
    0.08
    å²ij
    0.08
    .compiler
    0.08
    è´
    0.08
    kin
    0.08
     lun
    0.08
    Activations Density 0.069%

    No Known Activations