© 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. 36401
    Prev
    Next
    INDEX
    Explanations

    Gates said, City show, pilonidal disease

    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
    iasi
    -0.10
     tens
    -0.09
    аниÑİ
    -0.09
    éķ°
    -0.09
    -confirm
    -0.08
    ssel
    -0.08
    èĽĩ
    -0.08
    ancia
    -0.08
    SAT
    -0.08
    éĺĹ
    -0.08
    POSITIVE LOGITS
    æľĿ
    0.09
    èĢģçĪ·
    0.09
    çĪ¶åŃIJ
    0.09
    fold
    0.09
    æ·±æ·±åľ°
    0.08
    èĥĽ
    0.08
    conf
    0.08
    æīĵçĶµè¯Ŀ
    0.08
    è¶ĭåIJij
    0.08
    avan
    0.08
    Activations Density 0.006%

    No Known Activations