© 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. 24188
    Prev
    Next
    INDEX
    Explanations

    original/initial state

    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
    è§ī
    -0.10
    è¿Ļ件äºĭ
    -0.10
    è¿Ļ件äºĭæĥħ
    -0.09
    çļĦä¸ĸçķĮ
    -0.09
    oling
    -0.09
    覺
    -0.09
    isman
    -0.09
    _SIG
    -0.09
    åħīçݯ
    -0.09
    ä¸¤å¼ł
    -0.08
    POSITIVE LOGITS
     original
    0.28
    åİŁæĿ¥çļĦ
    0.27
    åİŁæľīçļĦ
    0.25
    åİŁæľī
    0.25
    åİŁæĿ¥
    0.23
    original
    0.21
     originally
    0.21
    åİŁä¾Ĩ
    0.20
    åİŁæľ¬
    0.20
    åİŁå§ĭ
    0.19
    Activations Density 0.238%

    No Known Activations