© 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. 37072
    Prev
    Next
    INDEX
    Explanations

    commenting on or tools

    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
    thest
    -0.10
    .uni
    -0.09
    ниÑĩ
    -0.09
    ç²¹
    -0.09
    jer
    -0.09
    hart
    -0.09
    bbing
    -0.09
    /her
    -0.09
    loom
    -0.09
    bies
    -0.08
    POSITIVE LOGITS
    aire
    0.12
    aires
    0.12
    ariat
    0.12
    ary
    0.10
    ant
    0.10
    aries
    0.09
    è
    0.09
     ÐĶм
    0.09
    家çĶ¨
    0.09
    åĨĽéĺŁ
    0.09
    Activations Density 0.177%

    No Known Activations