© 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. 31097
    Prev
    Next
    INDEX
    Explanations

    alkoxy-crosslinking one-component sealant materials

    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
    积累
    -0.10
    毯
    -0.09
    æł·åŃIJ
    -0.08
    ãģĮãģĭãģĭ
    -0.08
    åĺ»
    -0.08
     Bailey
    -0.08
    èķĥ
    -0.08
    æıIJåıĸ
    -0.08
    çĸıéĢļ
    -0.08
    ç³ĸå°¿
    -0.08
    POSITIVE LOGITS
    éħįæĸ¹
    0.12
     compat
    0.11
    æ²¥éĿĴ
    0.10
    ä½ĵç³»
    0.10
    æĶ¹
    0.10
    æłijèĦĤ
    0.10
    æ¶ĤæĸĻ
    0.10
     paints
    0.10
    åĢĻéĢī
    0.09
    åĪĨæķ£
    0.09
    Activations Density 0.431%

    No Known Activations