© 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. 6862
    Prev
    Next
    INDEX
    Explanations

    closing bracket or brace

    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
    ä¸įäºĨ
    -0.10
    åIJĦ项
    -0.09
    æĺ¯æ²¡æľī
    -0.08
    æĸ°æ¬¾
    -0.08
    çŃīå¤ļç§į
    -0.08
    åIJİèĢħ
    -0.08
    åı¨
    -0.08
    åIJİæĿ¥
    -0.08
    .APPLICATION
    -0.07
    çħ§æł·
    -0.07
    POSITIVE LOGITS
    estead
    0.10
    eren
    0.10
    å¾Īæĺİæĺ¾
    0.09
    gom
    0.09
     bounty
    0.09
    usc
    0.09
    .BorderColor
    0.09
    hsi
    0.09
    iosity
    0.09
    azel
    0.09
    Activations Density 0.029%

    No Known Activations