© 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. 19752
    Prev
    Next
    INDEX
    Explanations

    flame retardant panels

    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
    æĶ¶è´¹æłĩåĩĨ
    -0.10
    èĢ¶
    -0.09
    жд
    -0.09
    æIJ¬
    -0.09
    utas
    -0.08
    å°ıå°ı
    -0.08
    åŤ
    -0.08
    KeyValue
    -0.08
    åľ¨åIJĮä¸Ģ
    -0.08
    o
    -0.08
    POSITIVE LOGITS
    èĦĨ
    0.10
    USIC
    0.09
     import
    0.09
    åIJĬ顶
    0.09
    审ç¾İ
    0.09
    åħ¨æ°ij
    0.09
    çĩİ
    0.09
     wyb
    0.09
    åĬ¨åijĺ
    0.08
    <dynamic
    0.08
    Activations Density 0.059%

    No Known Activations