© 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. 11462
    Prev
    Next
    INDEX
    Explanations

    crustal thickness, cumulate, depreciation, reserves, bacterial ghosts

    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
    å¾Ĵ
    -0.09
    ä¸ĢæĬĬ
    -0.09
    æ°ĶåĢĻ
    -0.09
    æ²īæµ¸åľ¨
    -0.09
    adel
    -0.09
     Mor
    -0.09
    çĥŃ带
    -0.08
    æİ¥è¿ĩ
    -0.08
    快讯
    -0.08
    Produ
    -0.08
    POSITIVE LOGITS
    à¸ļา
    0.10
    å§ĵ
    0.09
    agu
    0.09
    Öĥ
    0.09
    çŀŃ
    0.09
    ä¸Ģ天
    0.09
    éĿ¢çĻ½
    0.08
    æī©åħħ
    0.08
    åĶĩ
    0.08
    ibur
    0.08
    Activations Density 0.033%

    No Known Activations