© 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. 11407
    Prev
    Next
    INDEX
    Explanations

    subject of, focus of

    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
    æķ¢
    -0.09
    身影
    -0.09
    éĺµåľ°
    -0.09
    ä»Ĺ
    -0.09
    MENT
    -0.09
     ÙĥاÙĦ
    -0.08
     Shr
    -0.08
    ogram
    -0.08
    asn
    -0.08
    ä¿¡ç®±
    -0.08
    POSITIVE LOGITS
    æ·Ŀ
    0.09
    讨论
    0.09
    äºīè®®
    0.09
    äºī论
    0.09
    éĩįçĤ¹åħ³æ³¨
    0.09
    纶
    0.09
    ç²¾å¯Ĩ
    0.09
    çĥŃè®®
    0.09
    ä¸įå°ıçļĦ
    0.08
    å¯ĨåĪĩåħ³æ³¨
    0.08
    Activations Density 0.106%

    No Known Activations