© 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. 32030
    Prev
    Next
    INDEX
    Explanations

    famous people's names

    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
    åĢĴéĹŃ
    -0.10
    è½±
    -0.10
    Ử
    -0.09
    å¾Īä½İ
    -0.09
     Nack
    -0.09
    åIJįåı«
    -0.09
    麻
    -0.09
    æī¿åĬŀ
    -0.09
     Coron
    -0.09
    �t
    -0.09
    POSITIVE LOGITS
    çļĦä¼Łå¤§
    0.09
    opath
    0.08
    ologie
    0.08
    çİĭåŃIJ
    0.07
    à°¦
    0.07
    Nam
    0.07
    æŃ£åľ¨
    0.07
     weighing
    0.07
    çĥ
    0.07
    ä¼Łå¤§çļĦ
    0.07
    Activations Density 0.052%

    No Known Activations