© 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. 56504
    Prev
    Next
    INDEX
    Explanations

    place names ending in -ia, -on, -eau

    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
    污æŁĵçī©
    -0.09
    ç»´å¥ĩ
    -0.09
    æĮĿ
    -0.08
    urtle
    -0.08
    çĤĻ
    -0.08
    udent
    -0.08
     înt
    -0.08
    çİ®
    -0.08
    è§Ĥèµı
    -0.08
    éķĸ
    -0.08
    POSITIVE LOGITS
    令人
    0.09
    æµij身
    0.09
    æĿ¥çļĦ
    0.09
    tility
    0.08
    arris
    0.08
     Lana
    0.08
    ä¼Ĭæĭī
    0.08
    æĿ¥å®¾
    0.08
    pel
    0.08
    åĨ²
    0.08
    Activations Density 0.095%

    No Known Activations