© 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. 20552
    Prev
    Next
    INDEX
    Explanations

    links and metadata

    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
    åIJİå¤ĩ
    -0.11
    imonial
    -0.09
    æľį
    -0.09
     kern
    -0.09
    åĵ©
    -0.09
    edList
    -0.08
    åıĭæĥħéĵ¾æİ¥
    -0.08
    .getOwnPropertyDescriptor
    -0.08
    åħ¥åĽŃ
    -0.08
     ÙħÙĨت
    -0.08
    POSITIVE LOGITS
    usat
    0.10
    æĬ¥éģĵ
    0.10
     Reuters
    0.09
     news
    0.09
    主è¦ģåĨħ容
    0.09
    æĬ¥éģĵ称
    0.09
    news
    0.09
    è¦ģéĹ»
    0.09
    iris
    0.09
    hana
    0.08
    Activations Density 0.340%

    No Known Activations