© 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. 36919
    Prev
    Next
    INDEX
    Explanations

    africa

    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
    ©
    -0.10
    год
    -0.09
    ìĩł
    -0.09
    åķ¬
    -0.09
    rink
    -0.09
    /frame
    -0.09
     Meadows
    -0.08
    urm
    -0.08
    çħ
    -0.08
    ä¸ŃåĽ½æĸĩåĮĸ
    -0.08
    POSITIVE LOGITS
    é»į
    0.10
    大éĻ¸
    0.10
    大éĻĨ
    0.10
    èħ¹
    0.09
    éħĭ
    0.09
    æĤĮ
    0.09
    emd
    0.08
    orgh
    0.08
    ALLY
    0.08
    all
    0.08
    Activations Density 0.029%

    No Known Activations