© 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. 63848
    Prev
    Next
    INDEX
    Explanations

    own

    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
    HDR
    -0.09
    utra
    -0.09
    iator
    -0.09
    .Cascade
    -0.08
    ç¹ģ
    -0.08
    utas
    -0.08
    åıªè¦ģæľī
    -0.08
    czÄħ
    -0.08
    å¤ļä¹Ī
    -0.08
    åľŃ
    -0.08
    POSITIVE LOGITS
     own
    0.25
    èĩªå·±çļĦ
    0.24
    æľīèĩªå·±çļĦ
    0.22
    äºĨèĩªå·±çļĦ
    0.19
     Own
    0.18
    Own
    0.18
     eigenen
    0.18
    å±ŀäºİèĩªå·±
    0.17
    çĭ¬æľīçļĦ
    0.16
     riêng
    0.16
    Activations Density 0.056%

    No Known Activations