© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37145
    Prev
    Next
    INDEX
    Explanations

    amenities and facilities

    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
    èĦĬ
    -0.10
     büt
    -0.09
    upt
    -0.09
    oplevel
    -0.09
    ä¹ĭéģĵ
    -0.09
    伺
    -0.09
    ennes
    -0.09
    isse
    -0.09
    èĻ
    -0.09
    dess
    -0.08
    POSITIVE LOGITS
    åį¡æĭī
    0.10
    å·´æĭī
    0.09
    å¸Ľ
    0.08
    æľŁéĹ´
    0.08
    åıĸè¯ģ
    0.08
    çĮĬ
    0.08
    åĨĴåĩº
    0.08
    èĻļ空
    0.08
    åı¯çĶ¨äºİ
    0.08
    æŃ¦æľ¯
    0.08
    Activations Density 0.033%

    No Known Activations