© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8137
    Prev
    Next
    INDEX
    Explanations

    temple locations

    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
    æ»ĭåij³
    -0.12
    稻
    -0.09
    èIJĥ
    -0.09
    çĶŁæ´»
    -0.09
    èļľ
    -0.09
    æĻļæĬ¥
    -0.08
    obili
    -0.08
    è¿ħ
    -0.08
    第ä¸ĢæĿ¡
    -0.08
    è¿·æĥij
    -0.08
    POSITIVE LOGITS
    å§ĭ建äºİ
    0.15
    寺åºĻ
    0.14
    éģĹåĿĢ
    0.13
    ä¸Ģ座
    0.12
    建çŃijçī©
    0.12
    设æĸ½
    0.11
    建çŃij
    0.11
    åĿĢ
    0.11
    åºĻ
    0.11
    è¿Ļ座
    0.10
    Activations Density 0.130%

    No Known Activations