© 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. 58454
    Prev
    Next
    INDEX
    Explanations

    hospitality and hosting

    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
    ä¸ĭä¸Ģ个
    -0.09
    à¸ĭา
    -0.09
    _pdata
    -0.08
    å²Ń
    -0.08
    PerPixel
    -0.08
    éĻŁ
    -0.08
    ypass
    -0.08
    å©´
    -0.08
    èĦ±ç¦»
    -0.08
    æĿī
    -0.08
    POSITIVE LOGITS
    æĭĽå¾ħ
    0.25
    æİ¥å¾ħ
    0.23
     hospitality
    0.21
     hosting
    0.16
     host
    0.16
     welcoming
    0.16
    host
    0.16
     hosts
    0.15
     Hosting
    0.15
    hosts
    0.15
    Activations Density 0.059%

    No Known Activations