© 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. 61698
    Prev
    Next
    INDEX
    Explanations

    consensus and opinion

    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
    履约
    -0.10
    ä¸į失
    -0.10
    æIJ¦
    -0.09
    èĩ³ä¸Ĭ
    -0.09
    æĢ§æł¼
    -0.08
    éĢĢè¿ĺ
    -0.08
    åĦĢ
    -0.08
    ä»ĸ人
    -0.08
    æĮİ
    -0.08
    vern
    -0.08
    POSITIVE LOGITS
    åħ±è¯Ĩ
    0.19
     consensus
    0.16
    主æµģ
    0.12
    èĪĨ论
    0.10
    è°ĥæŁ¥æĺ¾ç¤º
    0.10
    ç»Ŀ大å¤ļæķ°
    0.10
    çľĭæ³ķ
    0.09
     opinion
    0.09
    æ°ijæĦı
    0.09
    cons
    0.09
    Activations Density 0.064%

    No Known Activations