© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 64150
    Prev
    Next
    INDEX
    Explanations

    ship names and types

    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
    Negative Logits
    ä¸ĭ车
    -0.10
    jay
    -0.09
    路边
    -0.09
    车祸
    -0.09
     Martian
    -0.09
     Diss
    -0.08
     roadside
    -0.08
    èĩªçĦ¶ä¿ĿæĬ¤
    -0.08
    ellt
    -0.08
    温åĴĮ
    -0.08
    POSITIVE LOGITS
     vessels
    0.14
     vessel
    0.13
    èĪ¹èĪ¶
    0.12
    èīĺ
    0.12
    èĪ¹åıª
    0.11
    èĪªè¡Į
    0.11
    ä¸Ģèīĺ
    0.11
    èĪ´
    0.10
    è£ħè½½
    0.10
     ships
    0.10
    Activations Density 0.171%

    No Known Activations