© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 40133
    Prev
    Next
    INDEX
    Explanations

    crashing or crash

    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
    Negative Logits
    Ñģи
    -0.09
    泡泡
    -0.08
    -Cs
    -0.08
    æĮijæĪĺ
    -0.08
    æĮ¯å¥ĭ
    -0.08
    æķķ
    -0.08
    ãģ²
    -0.08
    çķ¢
    -0.08
    obs
    -0.08
    å°ıç»Ħ
    -0.08
    POSITIVE LOGITS
    ingly
    0.11
    åı¦ä¸Ģæĸ¹éĿ¢
    0.10
    edList
    0.10
    åħ¢
    0.10
    åĩºå±Ģ
    0.09
    åĿł
    0.09
    åľ¨æĦı
    0.09
    ides
    0.09
    <List
    0.09
    管çIJĨå±Ģ
    0.09
    Activations Density 0.025%

    No Known Activations