© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19986
    Prev
    Next
    INDEX
    Explanations

    Barack Obama

    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
    å¾Ī好
    -0.09
    rack
    -0.08
    UGE
    -0.08
    ennon
    -0.08
    éĽªå±±
    -0.08
    ä»Ĩ
    -0.08
     Margaret
    -0.08
    éªĮæĶ¶
    -0.08
    çŃ¹çłģ
    -0.07
    好çļĦ
    -0.07
    POSITIVE LOGITS
    лем
    0.11
    bps
    0.10
     zach
    0.09
    hani
    0.09
    è¯Ŀè¯Ń
    0.09
     @[
    0.09
    loat
    0.08
    caster
    0.08
    .snap
    0.08
    å¤ļäºĨ
    0.08
    Activations Density 0.020%

    No Known Activations