© 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. 37225
    Prev
    Next
    INDEX
    Explanations

    embedded in or with

    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
     expressive
    -0.09
    tram
    -0.08
     CRC
    -0.08
    _buckets
    -0.08
    ØŃÙģ
    -0.08
    COMMON
    -0.08
     zach
    -0.08
    å®ĮåĸĦ
    -0.08
    OCUS
    -0.08
    GetMethod
    -0.08
    POSITIVE LOGITS
    åµĮ
    0.24
    /embed
    0.18
     embed
    0.17
     Embed
    0.17
    .Embed
    0.16
     embedding
    0.16
    éķ¶åµĮ
    0.16
    (embed
    0.16
    .embed
    0.15
     Embedded
    0.15
    Activations Density 0.161%

    No Known Activations