© 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. 53263
    Prev
    Next
    INDEX
    Explanations

    requests starting with please

    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
    alyze
    -0.11
    æ¯ķç«Ł
    -0.10
    åħ¶å®ŀ
    -0.10
    åĪĿ次
    -0.09
    uate
    -0.09
    æĪĸå°Ĩ
    -0.09
    åħ¶å®ŀæĺ¯
    -0.09
    èĻ½è¯´
    -0.09
    iect
    -0.09
    å¾Īåı¯èĥ½
    -0.09
    POSITIVE LOGITS
    缨
    0.12
    åĭ¿
    0.11
    æŁ¬
    0.10
    åĭĻ
    0.09
     schön
    0.09
    äºĮåŃĹ
    0.09
    HeaderText
    0.09
    staking
    0.09
    çIJĨä¼ļ
    0.09
    noch
    0.09
    Activations Density 0.024%

    No Known Activations