© 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. 18193
    Prev
    Next
    INDEX
    Explanations

    time transitions

    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
    太å¤ļäºĨ
    -0.11
    åĨ¤
    -0.11
    ä¸įçĪ±
    -0.10
    plemented
    -0.10
    tering
    -0.10
    æĥ³äºĨ
    -0.09
     неÑĤ
    -0.09
    .sg
    -0.09
    管å±Ģ
    -0.09
    ãģĹãģŁãĤĤãģ®
    -0.08
    POSITIVE LOGITS
    槿
    0.09
    éĿŀ常
    0.08
     ability
    0.08
    اÙĥ
    0.08
    ritten
    0.08
    สว
    0.08
    æĪIJ为ä¸Ģ个
    0.08
    éľĢè¦ģçĶ¨
    0.08
    å¼ĥ
    0.08
    é£İåIJ¹
    0.08
    Activations Density 0.090%

    No Known Activations