© 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. 4990
    Prev
    Next
    INDEX
    Explanations

    place names ending in 'ia', 'ata', 'oc', 'on'

    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
     HOLDERS
    -0.09
     harbour
    -0.09
    èİ«åIJįåħ¶å¦Ļ
    -0.09
    çħħ
    -0.08
     Harbor
    -0.08
     Isles
    -0.08
     harbor
    -0.08
    /non
    -0.08
    åŁļ
    -0.08
    вл
    -0.08
    POSITIVE LOGITS
    æݸ
    0.09
    iev
    0.09
    indre
    0.09
    çģ°èī²
    0.09
    å¤ĸè¯Ń
    0.09
    åĮĹ约
    0.09
    èµł
    0.08
    åĨ°éĽª
    0.08
    éªģ
    0.08
    çĹħæ¯Ĵ
    0.08
    Activations Density 0.362%

    No Known Activations