© 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. 38569
    Prev
    Next
    INDEX
    Explanations

    cultural heritage and history

    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
    çĻ»
    -0.10
    ieri
    -0.09
    太æŀģ
    -0.09
    riba
    -0.09
     Astro
    -0.09
    çŃĭ
    -0.09
     Fleming
    -0.08
    ái
    -0.08
    VENT
    -0.08
    _seqs
    -0.08
    POSITIVE LOGITS
    æĤłä¹ħ
    0.16
    æĸĩåĮĸéģĹ产
    0.14
     heritage
    0.13
    herit
    0.13
    ä¼łç»ŁæĸĩåĮĸ
    0.12
    æĸĩåĮĸçļĦ
    0.12
    æ°ijæĹıæĸĩåĮĸ
    0.12
     history
    0.12
    åİĨåı²æĸĩåĮĸ
    0.11
     culture
    0.11
    Activations Density 0.071%

    No Known Activations