© 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. 2733
    Prev
    Next
    INDEX
    Explanations

    Morgan names and related places

    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
    ake
    -0.09
    ctor
    -0.09
    ä¹İ
    -0.09
    rior
    -0.09
    éģĵçIJĨ
    -0.09
    erner
    -0.09
    Ø´ÙĪ
    -0.08
    attery
    -0.08
     Jackets
    -0.08
    cake
    -0.08
    POSITIVE LOGITS
     dew
    0.09
    æįIJ款
    0.09
    å§Ĭ
    0.09
    çĦ¶èĢĮ
    0.09
    chaft
    0.08
    itarian
    0.08
    ously
    0.08
    ÂĢÂ
    0.08
    讦
    0.08
    绡
    0.08
    Activations Density 0.003%

    No Known Activations