© 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. 57788
    Prev
    Next
    INDEX
    Explanations

    have to

    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
    emics
    -0.10
    .AUTO
    -0.10
    صÙĪÙĦ
    -0.09
    形象
    -0.09
    ivers
    -0.09
    åıĻäºĭ
    -0.09
    çĤ³
    -0.09
    (<?
    -0.09
    认æ¸ħ
    -0.09
    åĩºéģĵ
    -0.09
    POSITIVE LOGITS
    好å¤ļ
    0.11
    å¾Ī强
    0.10
    æľĢå¤ļçļĦ
    0.10
    åīįçŀ»
    0.10
    äºĨä¸Ģ
    0.09
    å®īåħ¨éļIJæĤ£
    0.09
    å¾Īé«ĺ
    0.09
    gel
    0.08
    诸å¦Ĥ
    0.08
    æĢİ
    0.08
    Activations Density 0.311%

    No Known Activations