© 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. 12241
    Prev
    Next
    INDEX
    Explanations

    search process, committee, salary support, employment, teaching

    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
    ç¡ĸ
    -0.09
    _tm
    -0.09
    éĶĢæ¯ģ
    -0.09
     Pale
    -0.08
    fil
    -0.08
    åĪĨåħ¬åı¸
    -0.08
     confl
    -0.08
    _hal
    -0.08
    æĹłæīĢè°ĵ
    -0.08
    puter
    -0.08
    POSITIVE LOGITS
    æķĻèģĮå·¥
    0.15
    æķĻèĤ²æķĻåѦ
    0.12
     Teaching
    0.11
    åĬŀåѦ
    0.11
    èĤ²äºº
    0.11
    äºĭä¸ļåıijå±ķ
    0.10
    æĭĽçĶŁ
    0.10
    åħ¨æł¡
    0.10
    æķĻ
    0.10
     teaching
    0.10
    Activations Density 0.122%

    No Known Activations