© 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. 11468
    Prev
    Next
    INDEX
    Explanations

    phosphonate fragments

    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
    ipop
    -0.09
    级
    -0.09
    åį°
    -0.09
    å²·
    -0.08
    对å¾ħ
    -0.08
    侧éĿ¢
    -0.08
     Dayton
    -0.08
    DRV
    -0.08
    åıĪè¦ģ
    -0.08
    yal
    -0.08
    POSITIVE LOGITS
    åİŁåĽłä¹ĭä¸Ģ
    0.09
    æķĪåĬĽ
    0.09
    ardin
    0.09
    awah
    0.08
    ç²ij
    0.08
     Woodward
    0.08
    æĪ³
    0.08
    æĸ¤
    0.08
    æŃĩ
    0.08
    åIJ«ä¹ī
    0.08
    Activations Density 0.199%

    No Known Activations