© 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. 62563
    Prev
    Next
    INDEX
    Explanations

    not only

    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
    å¦Ĥæŀľä¸įæĺ¯
    -0.11
    igma
    -0.11
    æ³ĵ
    -0.10
    æĪĸå°Ĩ
    -0.10
    è¦ģä¹Ī
    -0.09
    大æ¦Ĥæĺ¯
    -0.09
    ä»Ģä¹Īåij¢
    -0.09
    æĢİä¹Īæł·
    -0.09
    å¦Ĥæŀľè¯´
    -0.09
    еÑģп
    -0.09
    POSITIVE LOGITS
    çľ¼åīįçļĦ
    0.09
    åįģåĪĨ
    0.08
    è¦ģçľĭ
    0.08
    ted
    0.08
    ục
    0.08
    iew
    0.08
    techn
    0.08
    侨
    0.08
    ãĤ¼
    0.08
    prüf
    0.08
    Activations Density 0.023%

    No Known Activations