© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10105
    Prev
    Next
    INDEX
    Explanations

    hosting

    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
    踵
    -0.10
    _ipc
    -0.09
    çī¹æ´¾
    -0.09
    åĪĨæŀIJå¸Ī
    -0.09
    æĥ³çŁ¥éģĵ
    -0.09
    åľ¨æ¸¸æĪıä¸Ń
    -0.09
    yal
    -0.08
     scri
    -0.08
    _INFORMATION
    -0.08
    派驻
    -0.08
    POSITIVE LOGITS
    æĬĬèĩªå·±çļĦ
    0.10
    å°ıå¾®ä¼ģä¸ļ
    0.09
    éħ·
    0.09
    建æĪIJåIJİ
    0.09
    .Storage
    0.09
     Sage
    0.08
     hosting
    0.08
    å°Ĩèĩªå·±çļĦ
    0.08
     GENERATED
    0.08
     Hosting
    0.08
    Activations Density 0.084%

    No Known Activations