© 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. 20377
    Prev
    Next
    INDEX
    Explanations

    tools and mechanisms

    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
    æĬ«
    -0.09
    èѦæĥķ
    -0.08
    éĻ¶
    -0.08
    Coal
    -0.08
     coalition
    -0.08
    èĦĺ
    -0.08
    èĨº
    -0.08
    zek
    -0.08
    5
    -0.08
    黾
    -0.08
    POSITIVE LOGITS
    çŃ·åŃIJ
    0.11
     scissors
    0.10
    çĸıæķ£
    0.10
    å·¥åħ·
    0.10
     kun
    0.09
    æĿłæĿĨ
    0.09
    èĬ¥
    0.09
    èī®
    0.09
    仪表
    0.09
     Kun
    0.09
    Activations Density 0.083%

    No Known Activations