© 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. 48323
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     fleece
    -0.09
    è¾ħ
    -0.09
    รา
    -0.08
    Restricted
    -0.08
    èµĥ
    -0.08
     Dalton
    -0.08
    çķĶ
    -0.08
     Corinthians
    -0.08
    被çĽĹ
    -0.08
    idges
    -0.08
    POSITIVE LOGITS
    åĨ²åĩ»
    0.12
    åį±
    0.10
    é¦Ĩ
    0.10
    æģIJé¾Ļ
    0.10
    æĴŀåĩ»
    0.09
    éĩįåIJ¯
    0.09
    è¹Ń
    0.09
    resh
    0.09
     habit
    0.08
     Manson
    0.08
    Activations Density 0.040%

    No Known Activations