© 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. 38671
    Prev
    Next
    INDEX
    Explanations

    part of Eigen

    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
    åĶ¯ä¸Ģ
    -0.10
    åı©
    -0.09
    éĢģåĩº
    -0.09
    æĭľ
    -0.08
    hte
    -0.08
     Ñĥме
    -0.08
    otton
    -0.08
    coop
    -0.08
    ål
    -0.08
     Humph
    -0.08
    POSITIVE LOGITS
    èIJ¥åķĨ
    0.08
    涵çĽĸäºĨ
    0.08
     Wass
    0.08
    è¿Ł
    0.08
    .ke
    0.08
     Fr
    0.08
    æĦŁåıĹåĪ°äºĨ
    0.08
     Rank
    0.08
    ITAL
    0.08
    èĢĮè¿Ļ
    0.08
    Activations Density 0.002%

    No Known Activations