© 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. 9344
    Prev
    Next
    INDEX
    Explanations

    event context

    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
    éªĦ
    -0.09
    æĪª
    -0.09
    icies
    -0.09
    acha
    -0.08
    -sn
    -0.08
    elo
    -0.08
    beginTransaction
    -0.08
    <Task
    -0.08
    _FRAMEBUFFER
    -0.08
    ä¸įèĪį
    -0.08
    POSITIVE LOGITS
    uality
    0.15
    =event
    0.14
    :Event
    0.13
     events
    0.13
    äºĭ件
    0.13
     event
    0.12
    /event
    0.12
    uate
    0.12
    ourcing
    0.12
    åıijçĶŁåľ¨
    0.11
    Activations Density 0.139%

    No Known Activations