© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6831
    Prev
    Next
    INDEX
    Explanations

    alpine regions and mountains

    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
    zelf
    -0.10
    lier
    -0.09
    lung
    -0.09
    ç¿Ļ
    -0.09
    piece
    -0.09
    åĵĦ
    -0.09
    rape
    -0.08
    lang
    -0.08
    fully
    -0.08
    åħ¥ãĤĮ
    -0.08
    POSITIVE LOGITS
    æľĭåıĭ们
    0.10
    æĦīå¿«
    0.09
     sẵn
    0.09
    大家ä¸Ģèµ·
    0.09
    iator
    0.09
    åĦ
    0.09
    ied
    0.09
    è£ģ
    0.09
    éªĭ
    0.08
    ç»ĵæĿŁäºĨ
    0.08
    Activations Density 0.010%

    No Known Activations