© 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. 56817
    Prev
    Next
    INDEX
    Explanations

    universities and their locations

    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
    åµĺ
    -0.09
    èŀĤ
    -0.08
    大åѦæ¯ķä¸ļ
    -0.08
    ounce
    -0.08
    ugins
    -0.08
    волÑĮ
    -0.08
    åħ³äºİæĪij们
    -0.08
    åħ¬åĬ¡åijĺ
    -0.08
    ä¸Ģ声
    -0.08
    ä¸Ńå°ıåŀĭ
    -0.08
    POSITIVE LOGITS
     Belmont
    0.09
    å§ĵ
    0.09
    itag
    0.09
    èĥĸåŃIJ
    0.08
    ãģĵãĤį
    0.08
     Pis
    0.08
    稷
    0.08
    æīģ
    0.08
     Blond
    0.08
    etty
    0.08
    Activations Density 0.009%

    No Known Activations