© 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. 2254
    Prev
    Next
    INDEX
    Explanations

    Skype or Dropbox

    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
    oir
    -0.11
    aceous
    -0.09
    åı£è¢ĭ
    -0.08
    ingo
    -0.08
    çĸ¤
    -0.08
    ä»ĸçŁ¥éģĵ
    -0.08
    own
    -0.08
    åij¸
    -0.08
    иÑĤелÑĮн
    -0.08
    iant
    -0.08
    POSITIVE LOGITS
    æĸĩæ¡Ī
    0.11
    çīĿ
    0.10
     Bride
    0.10
    åķ¾
    0.09
    jem
    0.09
    åįļ彩
    0.09
    ç°§
    0.09
    azzi
    0.09
    èIJ½
    0.09
    tes
    0.09
    Activations Density 0.010%

    No Known Activations