© 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. 38117
    Prev
    Next
    INDEX
    Explanations

    about quantities or numbers

    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
    ç½²
    -0.10
    åį³ä½¿æĺ¯
    -0.10
    cheid
    -0.09
    æķij人
    -0.09
    æĦıä¹ī
    -0.09
    ãģ¾ãģķ
    -0.09
    çģ«çĥ§
    -0.09
    èĸĩ
    -0.09
    æģ°
    -0.09
    VML
    -0.09
    POSITIVE LOGITS
    ä¸īåĽĽ
    0.12
     dozen
    0.10
    åĩłå¼ł
    0.10
    å°ı康
    0.10
    alf
    0.10
    两ä¸ī
    0.10
    ä¸į太
    0.09
    -about
    0.09
    çľĭä¸Ģä¸ĭ
    0.09
    atable
    0.08
    Activations Density 0.179%

    No Known Activations