© 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. 60705
    Prev
    Next
    INDEX
    Explanations

    if not, if any

    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
    pter
    -0.09
    ä¼ijæģ¯
    -0.09
    .hw
    -0.08
    berg
    -0.08
    htag
    -0.08
    æĹ©åľ¨
    -0.08
     ведÑĮ
    -0.08
    away
    -0.08
     elephant
    -0.08
    sei
    -0.07
    POSITIVE LOGITS
    çĶļèĩ³æĺ¯
    0.20
    ä¹ĥèĩ³
    0.18
    çĶļèĩ³
    0.16
     tháºŃm
    0.14
     íĺ¹ìĿĢ
    0.13
    åħ¶å®ĥéĹ®é¢ĺ
    0.11
    çĶļèĩ³è¿ĺ
    0.11
     sogar
    0.11
    ãģ©ãģĵãĤį
    0.10
    or
    0.10
    Activations Density 0.101%

    No Known Activations