© 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. 50924
    Prev
    Next
    INDEX
    Explanations

    addresses and locations

    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
    anter
    -0.08
    计åħ¥
    -0.08
    otto
    -0.08
     полов
    -0.07
    æĦıä¹ī
    -0.07
    /-
    -0.07
     ý
    -0.07
    sti
    -0.07
    al
    -0.07
    one
    -0.07
    POSITIVE LOGITS
    æĨĶ
    0.11
    å¼¼
    0.10
    .tel
    0.10
    éªİ
    0.10
    /twitter
    0.10
    éķĽ
    0.09
    StartupScript
    0.09
    /goto
    0.09
    ä¸Ģ带
    0.09
    ernen
    0.09
    Activations Density 0.016%

    No Known Activations