© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9518
    Prev
    Next
    INDEX
    Explanations

    what followed by a comparison

    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
    åįĪé¥Ń
    -0.10
    éĩįè¦ģçļĦ
    -0.10
     important
    -0.10
    çįĴ
    -0.09
    çĤ¹å¤ļ
    -0.09
     wichtig
    -0.09
     wicht
    -0.09
    éĩįè¦ģ
    -0.09
    æ£Ĵ
    -0.09
    äºĨä¸įå°ij
    -0.09
    POSITIVE LOGITS
    aland
    0.10
    æłĩå¿Ĺ
    0.09
    常æĢģ
    0.09
    èĩªæĿ¥
    0.09
    æĪijä»¬åľ¨
    0.09
    æľīä¸Ģ个
    0.09
    åĨįåĪ°
    0.08
    ande
    0.08
    常è§Ħ
    0.08
    ä¸ģ
    0.08
    Activations Density 0.161%

    No Known Activations