© 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. 33682
    Prev
    Next
    INDEX
    Explanations

    Belize and Honduras

    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
    çIJ¼
    -0.09
    纸ä¸Ĭ
    -0.09
    ä¸īäºļ
    -0.09
    splash
    -0.09
    åħµåĽ¢
    -0.09
    -any
    -0.09
    ή
    -0.08
    麾
    -0.08
    åħ¨æĹ¥åĪ¶
    -0.08
    éĢĿ
    -0.08
    POSITIVE LOGITS
    åIJİèĢħ
    0.09
    èĨĢ
    0.09
     Bun
    0.09
    craft
    0.09
    èĭĭ
    0.08
    quin
    0.08
    تر
    0.08
    agna
    0.08
     chin
    0.08
    prite
    0.08
    Activations Density 0.019%

    No Known Activations