© 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. 51039
    Prev
    Next
    INDEX
    Explanations

    all of

    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
    æĪĮ
    -0.10
    oves
    -0.09
    orsk
    -0.08
    æµĥ
    -0.08
    çİ©æĦı
    -0.08
    滹
    -0.08
    _mesh
    -0.08
    ä¸įæĥľ
    -0.08
    æ³½
    -0.08
    å°
    -0.08
    POSITIVE LOGITS
    项
    0.09
    æķ´ä¸ªäºº
    0.08
     mankind
    0.08
    èĮ«èĮ«
    0.08
    å·«
    0.08
    åĿĩåı¯
    0.08
    æĹħ游ä¸ļ
    0.08
    èµĦ
    0.08
    abant
    0.08
     Europe
    0.08
    Activations Density 0.027%

    No Known Activations