© 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. 6657
    Prev
    Next
    INDEX
    Explanations

    organizations and entities

    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
    èģĶè°Ĭ
    -0.09
     phil
    -0.09
    cul
    -0.09
    åIJįæł¡
    -0.09
    erta
    -0.08
     ceremonial
    -0.08
    èIJ¼
    -0.08
    Phil
    -0.08
     gala
    -0.08
    çĦ¶æĺ¯
    -0.08
    POSITIVE LOGITS
    æĥº
    0.10
    æµ®
    0.10
    é«¡
    0.09
    ÙĬض
    0.09
    otty
    0.09
    _blocked
    0.09
    dden
    0.09
    æ¶ĤæĸĻ
    0.09
    顽
    0.09
    å½ĵä¹ĭ
    0.08
    Activations Density 0.011%

    No Known Activations