© 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. 599
    Prev
    Next
    INDEX
    Explanations

    distance and range

    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
    é¢ī
    -0.13
    æ¼Ĥæµģ
    -0.09
    éĨį
    -0.09
    忤
    -0.09
    宿
    -0.09
    ç´«èī²
    -0.08
    çļĦèµĦéĩij
    -0.08
    é¢ļ
    -0.08
    å§Ĭ妹
    -0.08
    dens
    -0.08
    POSITIVE LOGITS
    è·Ŀ离
    0.24
    è·ĿéĽ¢
    0.21
    è¿ľå¤Ħ
    0.19
     distance
    0.19
    çļĦè·Ŀ离
    0.19
    distance
    0.17
    Distance
    0.16
    è¿ľ
    0.16
    _distance
    0.16
     Distance
    0.16
    Activations Density 0.065%

    No Known Activations