© 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. 64115
    Prev
    Next
    INDEX
    Explanations

    mapping to concepts or data

    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
    agli
    -0.09
    utsche
    -0.09
    人æ°ijæľįåĬ¡
    -0.08
    _FAST
    -0.08
    åĬłå¤§å¯¹
    -0.08
    GOOD
    -0.08
    举åĮĹ
    -0.08
    Ŀå§ĭ
    -0.08
    æ²ĵ
    -0.08
     spl
    -0.08
    POSITIVE LOGITS
    æĺł
    0.13
    _mapped
    0.12
     mapping
    0.11
     onto
    0.11
    .Mapper
    0.11
     mapped
    0.10
    mapped
    0.10
    mapping
    0.10
     Mapping
    0.10
    .Mapping
    0.09
    Activations Density 0.079%

    No Known Activations