© 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. 54299
    Prev
    Next
    INDEX
    Explanations

    but followed by contrasting information

    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
    ä¸įèĤ¯
    -0.09
    çĶŁæĢķ
    -0.09
    ore
    -0.09
    踱
    -0.09
    çļĦç¼ĺæķħ
    -0.09
    æ¯ķ
    -0.09
    ITTER
    -0.09
    解èĦ±
    -0.09
     therefore
    -0.08
     inse
    -0.08
    POSITIVE LOGITS
    è¾ĵç»Ļ
    0.09
    ä¸Ģé¦ĸ
    0.09
    éĩįéĩį
    0.09
    éĺ´è°ĭ
    0.09
    ÐIJÐĹ
    0.08
    失
    0.08
    éĺ´éĺ³
    0.08
     anchor
    0.08
    ä¸Ģåı¥
    0.08
    å¸ļ
    0.08
    Activations Density 0.023%

    No Known Activations