© 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. 7434
    Prev
    Next
    INDEX
    Explanations

    in shallow water or coastal areas

    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
    éħ£
    -0.11
    ropp
    -0.11
    çķĻç»Ļ
    -0.09
     Pest
    -0.09
    伫
    -0.09
    åįĥåı¤
    -0.08
    篷
    -0.08
    çĪ¨
    -0.08
    gor
    -0.07
    /Grid
    -0.07
    POSITIVE LOGITS
    éĵĦ
    0.10
    并ä¸įæĺ¯å¾Ī
    0.09
    ä¸ĸçķĮåIJĦåľ°
    0.09
    åıªè¦ģæľī
    0.09
    åijĻ
    0.09
    à¸Ńà¸Ń
    0.08
    ç¼ĺåĪĨ
    0.08
    ä¸Ĭå¹´
    0.08
    éĹ¹
    0.08
    çłĸ
    0.08
    Activations Density 0.337%

    No Known Activations