© 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. 34741
    Prev
    Next
    INDEX
    Explanations

    Sunday dates and phrases

    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
    ives
    -0.09
    ç»Ī身
    -0.09
    aston
    -0.09
    å±±åİ¿
    -0.08
    åIJĦæł·
    -0.08
    æ²¥
    -0.08
    å¿ł
    -0.08
    èľ¿
    -0.08
    ä»Ļ女
    -0.08
    头éĥ¨
    -0.08
    POSITIVE LOGITS
    nier
    0.10
     inout
    0.09
    atham
    0.09
    trace
    0.09
    妹妹
    0.09
    lord
    0.08
    rox
    0.08
    orum
    0.08
    rug
    0.08
    anzi
    0.08
    Activations Density 0.030%

    No Known Activations