© 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. 63619
    Prev
    Next
    INDEX
    Explanations

    standalone parts or components

    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
    reuse
    -0.11
    ENER
    -0.09
    贯穿
    -0.09
    æµģ转
    -0.09
    /cms
    -0.09
    æķ´æĶ¹æݪæĸ½
    -0.09
    wake
    -0.09
    æ¿Ģ
    -0.09
    éªŀ
    -0.09
    Ñħод
    -0.09
    POSITIVE LOGITS
    åĩŃ
    0.09
    å¼ıçļĦ
    0.09
    å°ģ
    0.08
    gger
    0.08
    æĢ§å¼º
    0.08
     explanatory
    0.08
    åĽłèĢĮ
    0.08
    佩æľį
    0.08
    å¼ı
    0.08
     Morr
    0.08
    Activations Density 0.028%

    No Known Activations