© 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. 49201
    Prev
    Next
    INDEX
    Explanations

    container, bowl, vessel

    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
    å°¾
    -0.10
    éªĪ
    -0.09
    _DP
    -0.09
     Lager
    -0.09
    ä¿®åīª
    -0.09
    åī½
    -0.09
     Burger
    -0.09
    骥
    -0.08
    人æµģ
    -0.08
    elps
    -0.08
    POSITIVE LOGITS
    容åĻ¨
    0.18
     container
    0.14
    缼
    0.14
    ç¢Ĺ
    0.13
     bowl
    0.13
     bowls
    0.12
    container
    0.12
     containers
    0.12
    æĿ¯åŃIJ
    0.12
     vessel
    0.11
    Activations Density 0.082%

    No Known Activations