© 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. 10147
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities like billions

    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
    /news
    -0.09
    æ±Ģ
    -0.09
    管çIJĨä¸Ńå¿ĥ
    -0.09
    çĻŀ
    -0.09
     ТÑĥÑĢ
    -0.09
     Voy
    -0.09
    геÑĢ
    -0.08
    é²ģ
    -0.08
    æľĪä¸Ń
    -0.08
    Ñģад
    -0.08
    POSITIVE LOGITS
    请çĤ¹åĩ»
    0.11
    ä¸į容æĺĵ
    0.10
    è¿Ľåĩº
    0.09
    ä¸įåħį
    0.09
    acher
    0.08
    å°±è¿Ļä¹Ī
    0.08
    空æ°ĶåĩĢåĮĸ
    0.08
    å®ĥæĺ¯
    0.08
    ä¸įè¡Į
    0.08
    縻
    0.08
    Activations Density 0.050%

    No Known Activations