© 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. 30453
    Prev
    Next
    INDEX
    Explanations

    association in records, liquid crystal, ism spectrum

    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
    讫
    -0.10
    åľ¬
    -0.09
    碴
    -0.09
    antino
    -0.09
    loom
    -0.09
    ãģ£ãģ±
    -0.09
    ศา
    -0.08
    æįĨ
    -0.08
    æĶ¶è´Ń
    -0.08
    è¿·
    -0.08
    POSITIVE LOGITS
    åħĪ天
    0.10
    è¦ģçľĭ
    0.10
     Aqu
    0.09
    èĩ£
    0.09
    çī¹è´¨
    0.09
    æĻļä¼ļ
    0.08
    ç»Łæ²»
    0.08
    нÑİ
    0.08
    å¯Įè´µ
    0.08
    ä¸īæĸ¹
    0.08
    Activations Density 0.015%

    No Known Activations