© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 3017
    Prev
    Next
    INDEX
    Explanations

    already followed by past action

    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
    Negative Logits
    åĪĩå°Ķ
    -0.10
    éĻĭ
    -0.09
    æĮ«
    -0.09
    æµĵæµĵçļĦ
    -0.09
    bgcolor
    -0.09
    ÙħاÙĦ
    -0.09
    奴
    -0.09
    dued
    -0.08
    åºĶæĶ¶
    -0.08
    被迫
    -0.08
    POSITIVE LOGITS
    rien
    0.11
    éĢĿ
    0.10
    _Action
    0.09
     давно
    0.09
    wargs
    0.09
    çŁ¥
    0.09
    kinson
    0.09
    anka
    0.08
    åĩłåįĥ
    0.08
    edException
    0.08
    Activations Density 0.031%

    No Known Activations