© 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. 6575
    Prev
    Next
    INDEX
    Explanations

    people from regions ending in 'ian' or 'an'

    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
    çļĦ人éĥ½
    -0.12
    viously
    -0.10
    lessly
    -0.10
    人æ°ijæľįåĬ¡
    -0.10
    å¤ļåħĥåĮĸ
    -0.10
    æ´¾åĩº
    -0.10
    å°Ķæĸ¯
    -0.09
    æŁĵ
    -0.09
    fully
    -0.09
    ç¢ĵ
    -0.09
    POSITIVE LOGITS
    ischen
    0.09
    imo
    0.09
    yal
    0.08
    ismo
    0.08
    innen
    0.08
    alia
    0.08
    ÑĤен
    0.08
     McConnell
    0.08
    ische
    0.08
     ingen
    0.08
    Activations Density 0.073%

    No Known Activations