© 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. 19087
    Prev
    Next
    INDEX
    Explanations

    Regency, regents, regardless

    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
    -0.10
    oku
    -0.10
    éļĻ
    -0.09
    bear
    -0.09
    gether
    -0.09
    ç¼ĿéļĻ
    -0.09
    /or
    -0.09
    edges
    -0.09
     reven
    -0.08
    ãģĿãĤĮãģ«
    -0.08
    POSITIVE LOGITS
    ardless
    0.13
    èIJ½ãģ¡
    0.11
    ensburg
    0.11
    /reg
    0.11
    æĦıä¹īä¸Ĭ
    0.10
    ONTAL
    0.10
    gie
    0.10
    enerate
    0.10
    æĦıä¹īä¸ĬçļĦ
    0.10
    ulatory
    0.10
    Activations Density 0.065%

    No Known Activations