© 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. 38866
    Prev
    Next
    INDEX
    Explanations

    equals People

    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
    çı
    -0.09
     Tenn
    -0.09
    dag
    -0.09
    7
    -0.08
    plementation
    -0.08
    æķ¬è¯·
    -0.08
    0
    -0.08
    åħ¶ä»ĸçļĦ
    -0.08
     Hab
    -0.08
    çĶļèĩ³æĺ¯
    -0.08
    POSITIVE LOGITS
    /=
    0.12
    ä»Ģä¹Īåij¢
    0.10
    å½¹
    0.09
    èĭ¾
    0.09
    bbie
    0.09
    æĺī
    0.09
    ä¸įåĨį
    0.09
    çļĦå°±æĺ¯
    0.08
    梦æĥ³
    0.08
    ä¸įæŃ¢
    0.08
    Activations Density 0.181%

    No Known Activations