© 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. 1018
    Prev
    Next
    INDEX
    Explanations

    deep business interaction

    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
    ruc
    -0.11
    大æĸ¹
    -0.09
    UnderTest
    -0.08
    ting
    -0.08
    æ®Ĩ
    -0.08
    ile
    -0.08
     lÃłnh
    -0.08
    æĶĺ
    -0.08
    ably
    -0.08
    æĪ®
    -0.08
    POSITIVE LOGITS
    ening
    0.16
    ened
    0.14
    pling
    0.11
    (er
    0.11
    acre
    0.10
    æµħ
    0.10
    æĥħ人
    0.10
    ç»Ĩèĩ´
    0.10
    lings
    0.10
    æ¹¾
    0.09
    Activations Density 0.029%

    No Known Activations