© 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. 51702
    Prev
    Next
    INDEX
    Explanations

    .exception, adapter, jobs, console

    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
    Busy
    -0.09
     sorts
    -0.08
    èĩªæĦ¿
    -0.08
    estr
    -0.08
    SORT
    -0.08
    çŀ¬
    -0.08
    aida
    -0.08
    chia
    -0.08
     Stall
    -0.08
    ISON
    -0.08
    POSITIVE LOGITS
    åĵij
    0.10
    éĴŀ
    0.09
     kald
    0.09
    ç½ijé¦ĸ页
    0.09
    豫
    0.09
    驼
    0.09
    åĮĹè·¯
    0.09
    驺
    0.09
    äºĮæľŁ
    0.08
    åı
    0.08
    Activations Density 0.389%

    No Known Activations