© 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. 37186
    Prev
    Next
    INDEX
    Explanations

    research, design, services, advice

    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
     Ade
    -0.09
    unga
    -0.09
    aida
    -0.09
     Herc
    -0.08
    檬
    -0.08
    ä¸Ģèĩ´æĢ§
    -0.08
    pery
    -0.08
     adequ
    -0.08
    å¿ĥ缮ä¸Ń
    -0.08
    _FM
    -0.08
    POSITIVE LOGITS
    éĴµ
    0.10
    åŃº
    0.09
    /social
    0.09
    loth
    0.09
    esModule
    0.09
    éĺ²å®Ī
    0.08
    icals
    0.08
     ÐľÐ¾Ñģков
    0.08
    åįĩ级æĶ¹éĢł
    0.08
     ÑĤож
    0.08
    Activations Density 0.080%

    No Known Activations