© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 17338
    Prev
    Next
    INDEX
    Explanations

    coastline, island, sea, ocean

    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
    沿海
    -0.13
    æµ·è¾¹
    -0.13
    æµ·æ´ĭ
    -0.12
    海滨
    -0.11
    æµ·æ°´
    -0.11
    Ocean
    -0.11
    海滩
    -0.11
    海岸
    -0.10
    å²Ľ
    -0.10
     ÐŀÑĩ
    -0.10
    POSITIVE LOGITS
    ä¸įèĪį
    0.10
     favorite
    0.10
    大å®Ĺ
    0.09
    lix
    0.09
    ä¸ĭåįĬå¹´
    0.09
    è¥Ħ
    0.08
     Favorite
    0.08
    æľĢåĸľæ¬¢
    0.08
     favorites
    0.08
    AUSE
    0.08
    Activations Density 0.276%

    No Known Activations