© 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. 62210
    Prev
    Next
    INDEX
    Explanations

    distribution across the world

    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
    æľīçļĦ
    -0.09
     diplom
    -0.09
    è¿Ľåİ»
    -0.08
    ner
    -0.08
    ä¸Ģ个人
    -0.08
    åı¯ä¾Ľ
    -0.08
    æĢ»æľī
    -0.08
    íĽĦ
    -0.08
     Ñĩеловек
    -0.08
    1
    -0.08
    POSITIVE LOGITS
    第ä¸ī个
    0.10
    座
    0.10
    WAYS
    0.10
    .stub
    0.09
    æĥĨ
    0.08
    arias
    0.08
    LOB
    0.08
    æį£
    0.08
    ToLower
    0.08
    osos
    0.08
    Activations Density 0.030%

    No Known Activations