© 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. 8190
    Prev
    Next
    INDEX
    Explanations

    design firm, director, collection

    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
    ãģĦãģıãĤī
    -0.09
    å¿ĹæĦ¿
    -0.08
    rowable
    -0.08
    ãĤĦãĤĬ
    -0.08
    åį¡éĢļ
    -0.08
    ombat
    -0.08
    åĽ½å®¶éĩįçĤ¹
    -0.08
    bilder
    -0.08
    rowCount
    -0.08
    _PRIORITY
    -0.08
    POSITIVE LOGITS
    设计å¸Ī
    0.14
    设计
    0.12
     design
    0.12
     designers
    0.11
     designer
    0.11
    çļĦ设计
    0.11
     Design
    0.10
    esign
    0.10
    .design
    0.10
    IDEO
    0.10
    Activations Density 0.164%

    No Known Activations