© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9128
    Prev
    Next
    INDEX
    Explanations

    horse and ribbon

    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
    alls
    -0.09
    jab
    -0.08
    èĬ°
    -0.08
    ä¼
    -0.08
     hole
    -0.07
    ä¸Ģ楼
    -0.07
    ä¸ĢäºĮ
    -0.07
     holes
    -0.07
     Miss
    -0.07
    ention
    -0.07
    POSITIVE LOGITS
    yre
    0.11
    olate
    0.11
    èµ°ä¸ĭåİ»
    0.10
    presso
    0.10
    craper
    0.10
    è°ij
    0.10
    .Fore
    0.09
    chwitz
    0.09
    елÑĮ
    0.09
    ño
    0.09
    Activations Density 0.005%

    No Known Activations