© 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. 7354
    Prev
    Next
    INDEX
    Explanations

    maritime matters

    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
    uhn
    -0.10
    åŀ«
    -0.09
     Vid
    -0.09
    vid
    -0.09
    è°Ł
    -0.09
    urr
    -0.09
    æ´ĹèĦ¸
    -0.08
    ãĥ¯ãĤ¤
    -0.08
    /meta
    -0.08
    BIND
    -0.08
    POSITIVE LOGITS
    æİIJ
    0.11
     vessels
    0.11
    èĪ¹èĪ¶
    0.10
    ÑģÑĤо
    0.10
    èĪ¹åıª
    0.10
    èĪªè¡Į
    0.09
    ç»·
    0.09
    ä¸ĩåħ¬éĩĮ
    0.09
     vessel
    0.09
    nings
    0.09
    Activations Density 0.099%

    No Known Activations