© 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. 17534
    Prev
    Next
    INDEX
    Explanations

    invitation to receive link or update

    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
    æļ´é£İ
    -0.09
     Pun
    -0.09
    é£İæļ´
    -0.09
    å¸Ĥåľºä»·æł¼
    -0.09
     вообÑīе
    -0.09
    _CHIP
    -0.09
    æĥ©ç½ļ
    -0.09
    æĺĤ
    -0.09
    ighth
    -0.08
    æĥ©
    -0.08
    POSITIVE LOGITS
     Emanuel
    0.09
    æ·ij
    0.09
    REV
    0.09
    稿
    0.09
    éĩĮéĿ¢æľī
    0.08
    åºĶ注æĦı
    0.08
    ibern
    0.08
    æIJºå¸¦
    0.08
    妹åŃIJ
    0.08
    æĮĽ
    0.08
    Activations Density 0.039%

    No Known Activations