© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52991
    Prev
    Next
    INDEX
    Explanations

    close to

    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
     geg
    -0.09
    _Tab
    -0.09
     Sle
    -0.08
     sỼm
    -0.08
    ç»ĦåĽ¢
    -0.08
    avar
    -0.08
    æijĺ
    -0.08
    ouse
    -0.08
    enario
    -0.08
     improv
    -0.08
    POSITIVE LOGITS
    edin
    0.11
    baugh
    0.10
    åĩºåĬ¨
    0.10
    Sir
    0.09
    饯
    0.09
    æľºåĬ¨
    0.09
    å¾Īæĺ¯
    0.09
    æ¯Ķéĩį
    0.09
    hazi
    0.08
    åŁł
    0.08
    Activations Density 0.233%

    No Known Activations