© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50672
    Prev
    Next
    INDEX
    Explanations

    economic/news updates

    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
    èĦĶ
    -0.10
    åīľ
    -0.09
    çIJīçĴĥ
    -0.09
    åķĸ
    -0.09
    æı½
    -0.08
     Shine
    -0.08
    ä¸įå¿ĺ
    -0.08
    éĺµ
    -0.08
    èij©
    -0.08
    cars
    -0.08
    POSITIVE LOGITS
    åĩºæĿ¥äºĨ
    0.09
    ulo
    0.09
    thic
    0.08
    åĸĦæĦı
    0.08
    .touch
    0.08
    æĸĻ
    0.08
    éĢıéľ²
    0.08
    ç¿Į
    0.08
    inator
    0.08
    æѧ
    0.08
    Activations Density 0.014%

    No Known Activations