© 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. 8965
    Prev
    Next
    INDEX
    Explanations

    time or creation events

    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
    康
    -0.09
    å¹ķ
    -0.08
     Kear
    -0.08
    onte
    -0.08
     mediator
    -0.08
    2
    -0.08
     Gra
    -0.08
    çİ»
    -0.08
    çݯ
    -0.08
    éĤ¬
    -0.07
    POSITIVE LOGITS
    ä¸İåIJ¦
    0.13
    è¿ĩçļĦ
    0.10
     Eag
    0.09
     trif
    0.09
    åĶ®åIJİ
    0.09
     McGr
    0.09
     cub
    0.08
     <!--[
    0.08
    _rf
    0.08
     cle
    0.08
    Activations Density 0.182%

    No Known Activations