© 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. 55400
    Prev
    Next
    INDEX
    Explanations

    $Id$ marker

    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
    irim
    -0.09
    à¸Ńà¸ģ
    -0.09
    æĭĻ
    -0.08
    SCP
    -0.08
    æľµ
    -0.08
    -Jan
    -0.08
    èµĦ
    -0.08
     má»Ļ
    -0.08
     nonatomic
    -0.08
    ajas
    -0.08
    POSITIVE LOGITS
    spiel
    0.09
    çľĭå¾Ĺ
    0.09
    èļĬ
    0.09
    ru
    0.09
    iards
    0.09
    licit
    0.09
    äºĭåIJİ
    0.08
    ires
    0.08
     bè
    0.08
    andard
    0.08
    Activations Density 0.214%

    No Known Activations