© 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. 26906
    Prev
    Next
    INDEX
    Explanations

    linear and nonlinear phenomena

    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
    ä¹İ
    -0.10
    åĴĮæĬĢæľ¯
    -0.09
    .toObject
    -0.09
    รา
    -0.09
    ãĤĭãĤĪãģĨãģ«
    -0.09
    çķĻä½ı
    -0.09
    çļĦéĩįçĤ¹
    -0.09
    æĭĸæ¬ł
    -0.09
    ARA
    -0.09
    atest
    -0.09
    POSITIVE LOGITS
    åºĦåĽŃ
    0.10
    éĥĩ
    0.09
    主æĦı
    0.09
    edList
    0.09
    èĦIJ
    0.08
    allen
    0.08
    cue
    0.08
    ressed
    0.08
    åѤç«ĭ
    0.08
    ائز
    0.08
    Activations Density 0.028%

    No Known Activations