© 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. 2228
    Prev
    Next
    INDEX
    Explanations

    between two concepts

    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
    åºı
    -0.09
    ALAR
    -0.09
    urator
    -0.08
    æĬ¬å¤´
    -0.08
    3
    -0.08
    解å¼Ģ
    -0.08
    çŃīä¸Ģæī¹
    -0.08
    尾巴
    -0.08
    1
    -0.08
    Witness
    -0.08
    POSITIVE LOGITS
    èµ°ä¸Ĭ
    0.11
    æľīçĤ¹
    0.10
    æĪIJ为
    0.10
    ä»Ģä¹Īæĺ¯
    0.09
    å¯Į豪
    0.09
    è´
    0.09
     outright
    0.09
     downright
    0.09
    OSE
    0.09
    utes
    0.09
    Activations Density 0.037%

    No Known Activations