© 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. 50988
    Prev
    Next
    INDEX
    Explanations

    east/west coast

    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
    æľ
    -0.08
    åŃĹåı·
    -0.08
     Loaded
    -0.08
    ored
    -0.08
     drift
    -0.08
    redd
    -0.08
     drifting
    -0.08
    енÑĮк
    -0.07
    ä¸į太
    -0.07
     nou
    -0.07
    POSITIVE LOGITS
    海岸
    0.15
    岸
    0.12
     coast
    0.11
    海滨
    0.10
     shore
    0.10
    æµ·è¾¹
    0.10
     shores
    0.10
     беÑĢ
    0.10
    é¢ł
    0.10
     coastline
    0.10
    Activations Density 0.097%

    No Known Activations