© 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. 52430
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by definite articles

    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
    ermen
    -0.09
    åıĺå¼Ĥ
    -0.09
    :http
    -0.09
     ×ķ×Ķ×ķ×IJ
    -0.09
    æĢĸ
    -0.09
    çݳ
    -0.09
    ÑıÑħ
    -0.09
    FilterWhere
    -0.08
    åĵ¥
    -0.08
     Gord
    -0.08
    POSITIVE LOGITS
     someone
    0.10
    ä¸Ģæŀ¶
    0.09
    ä¸Ģ个人
    0.09
    æŁIJ
    0.09
     your
    0.09
     somebody
    0.08
    aland
    0.08
     a
    0.08
    æĪijåıijçİ°
    0.08
    æIJŀ
    0.08
    Activations Density 0.508%

    No Known Activations