© 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. 20333
    Prev
    Next
    INDEX
    Explanations

    — Paul— Ajay— War— Cong— Rev— 1—,— allow

    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
    ResourceId
    -0.10
    SimpleName
    -0.10
    arto
    -0.09
    asted
    -0.09
    鸾
    -0.09
    à¸Ńาศ
    -0.09
    ular
    -0.09
    ään
    -0.09
    æ¶ķ
    -0.09
    ÂŃs
    -0.09
    POSITIVE LOGITS
    å¨ģåĬĽ
    0.10
    èĭı
    0.09
    å¯ĵæĦı
    0.09
    æĿĥå¨ģ
    0.08
    æŶæķĪ
    0.08
    tion
    0.08
    æĩĴ
    0.08
    èĺĩ
    0.08
    uman
    0.08
    incy
    0.08
    Activations Density 0.073%

    No Known Activations