© 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. 8938
    Prev
    Next
    INDEX
    Explanations

    project phases or studies

    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
    æı½
    -0.10
    ream
    -0.10
    éļıæŶ
    -0.10
    extr
    -0.09
    è¾ĺ
    -0.09
    ',['../
    -0.09
    askan
    -0.09
    çľĭä¸Ģçľĭ
    -0.09
    çłĶ究ä¸Ńå¿ĥ
    -0.09
    çīĪæĿĥæīĢæľī
    -0.09
    POSITIVE LOGITS
    æľŁéĹ´
    0.10
    éĺ¶æ®µ
    0.09
     phase
    0.09
    以æĿ¥
    0.09
    æľŁåĨħ
    0.09
    è¿Ļåĩłå¤©
    0.09
    è¿Ļ两天
    0.08
     alone
    0.08
     Alone
    0.08
    åĩłæ¬¡
    0.08
    Activations Density 0.056%

    No Known Activations