© 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. 22682
    Prev
    Next
    INDEX
    Explanations

    geographical locations and programming languages

    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
     Wise
    -0.11
    缨
    -0.09
    ä»İä¸Ń
    -0.09
    wise
    -0.09
    ä¸Ģ个æĺŁæľŁ
    -0.08
    ï¼Į并
    -0.08
    bru
    -0.08
    以æѤ
    -0.08
    æŃ£åĢ¼
    -0.08
    -ahead
    -0.08
    POSITIVE LOGITS
     Ñĩего
    0.10
    çļĦ人éĥ½
    0.09
    åĬŀ好
    0.09
    çļĦæĬķèµĦ
    0.09
     Ronald
    0.09
    çļĦä¸ĢåĪĩ
    0.09
    浯
    0.09
    singleton
    0.08
    绫
    0.08
    Convertible
    0.08
    Activations Density 0.499%

    No Known Activations