© 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. 51312
    Prev
    Next
    INDEX
    Explanations

    looting or raiding

    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
     Ñĥд
    -0.09
    éĻ·åħ¥äºĨ
    -0.08
    æį
    -0.08
    æľīèĥ½åĬĽ
    -0.08
    IS
    -0.08
     Judy
    -0.08
    .MODE
    -0.08
    ãģĩ
    -0.08
    ä¸įèĥ½åĨį
    -0.08
    illet
    -0.08
    POSITIVE LOGITS
    edException
    0.14
    stash
    0.09
    å¿Ļ
    0.09
    สาร
    0.09
    uml
    0.09
    ç®±
    0.08
    eer
    0.08
    erp
    0.08
    ë°°
    0.08
    cope
    0.08
    Activations Density 0.009%

    No Known Activations