© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52338
    Prev
    Next
    INDEX
    Explanations

    repeat or again

    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
     Boulder
    -0.09
    .lift
    -0.08
    .cmb
    -0.08
    HS
    -0.08
    éĺģ
    -0.08
     Coll
    -0.08
    æĺĨ
    -0.08
    æıIJæĹ©
    -0.08
    éĢĬ
    -0.08
     straight
    -0.08
    POSITIVE LOGITS
    åĨį次
    0.24
    åĨį度
    0.19
    åĨįä¸Ģ次
    0.18
    第äºĮ次
    0.18
     again
    0.17
    äºĮ次
    0.16
    第äºĮæī¹
    0.16
     nữa
    0.16
    åıĪä¸Ģ次
    0.16
     Ñģнова
    0.16
    Activations Density 0.276%

    No Known Activations