© 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. 55509
    Prev
    Next
    INDEX
    Explanations

    trade unions and associations

    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
    mgr
    -0.10
    çī¹éķ¿
    -0.09
    åı¹
    -0.08
    åĦĺ
    -0.08
    è§ĦèĮĥ
    -0.08
    åľ°å¤Ħ
    -0.08
    alex
    -0.08
    Runner
    -0.08
    æĭĵå±ķ
    -0.08
    named
    -0.08
    POSITIVE LOGITS
    /Public
    0.09
    主å¸Ń
    0.09
    ä¾
    0.09
    èĨĤ
    0.09
    è¦ģæĬĬ
    0.08
    è¦ģåģļ
    0.08
     Mét
    0.08
    ÙĤابÙĦ
    0.08
    .OP
    0.08
    æĺı
    0.08
    Activations Density 0.024%

    No Known Activations