© 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. 17032
    Prev
    Next
    INDEX
    Explanations

    pockets

    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
    åĿį
    -0.10
    åѦåłĤ
    -0.09
    æĸ½
    -0.09
    pivot
    -0.09
    å¤ļ彩
    -0.08
    è±¹
    -0.08
    åįĪ
    -0.08
    æķ´
    -0.08
    æĶ¾çľ¼
    -0.08
     pivot
    -0.08
    POSITIVE LOGITS
    ihu
    0.09
    æı£
    0.09
    åıįè¿ĩæĿ¥
    0.08
    æľĪä¸ĭæŬ
    0.08
    è£ĺ
    0.08
    çĹ°
    0.08
    æ°ijæĹı
    0.08
    深深çļĦ
    0.08
    å¾µ
    0.08
    çĹĤ
    0.08
    Activations Density 0.015%

    No Known Activations