© 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. 39466
    Prev
    Next
    INDEX
    Explanations

    Brent or Trent

    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
    éģij
    -0.11
     اÙĦزÙħÙĨ
    -0.11
    ãĤº
    -0.11
    ä»Ĺ
    -0.11
    keit
    -0.10
    atical
    -0.10
    ../../../
    -0.10
    -minded
    -0.09
    mente
    -0.09
    æĹ»
    -0.09
    POSITIVE LOGITS
    enance
    0.11
    eur
    0.11
    or
    0.10
    egers
    0.09
    ez
    0.09
    o
    0.09
    wright
    0.09
    ville
    0.09
    azar
    0.09
    orio
    0.08
    Activations Density 0.011%

    No Known Activations