© 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. 21366
    Prev
    Next
    INDEX
    Explanations

    finest quality ingredients and materials

    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
    ipped
    -0.09
    äºĭæ¥Ń
    -0.09
    /operator
    -0.09
     SEC
    -0.09
    plet
    -0.08
    深深
    -0.08
    _launch
    -0.08
    两次
    -0.08
    åĬĿ
    -0.08
    èµ
    -0.08
    POSITIVE LOGITS
     ingredients
    0.17
     materials
    0.17
    æĿIJæĸĻ
    0.16
    åİŁæĿIJæĸĻ
    0.16
    æĿIJ
    0.16
    åİŁæĸĻ
    0.15
    materials
    0.15
    ç´łæĿIJ
    0.14
     Ingredients
    0.13
    é£ŁæĿIJ
    0.13
    Activations Density 0.069%

    No Known Activations