© 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. 6511
    Prev
    Next
    INDEX
    Explanations

    materials are provided

    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
    èĤļ
    -0.10
    ä¸įèĪį
    -0.09
    çĵ¶åŃIJ
    -0.09
    åĪ°æľĢåIJİ
    -0.09
    orca
    -0.09
    .gt
    -0.08
    ä¹ĭ人
    -0.08
     лиÑĨа
    -0.08
    poses
    -0.08
    å¼¢
    -0.08
    POSITIVE LOGITS
    é½IJåħ¨
    0.12
    ä¹ī
    0.10
    義
    0.10
    ils
    0.09
    egot
    0.09
    ÅĽci
    0.09
    AAD
    0.09
    åħħ足çļĦ
    0.08
    åĮħæĭ¬
    0.08
    æħİ
    0.08
    Activations Density 0.059%

    No Known Activations