© 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. 57020
    Prev
    Next
    INDEX
    Explanations

    well followed by word

    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
    glomer
    -0.10
    бил
    -0.09
    åĪ°æĿ¥
    -0.09
    é¢Ĩ导èĢħ
    -0.09
    IEL
    -0.09
    epam
    -0.09
    餮
    -0.09
    èĽ¾
    -0.09
    æīĢéľĢè¦ģ
    -0.08
    åŃª
    -0.08
    POSITIVE LOGITS
    ness
    0.11
    ä¼ĹæīĢåij¨çŁ¥
    0.10
    åģļè¿ĩ
    0.09
    å·²ä¹ħçļĦ
    0.09
    -known
    0.09
    edu
    0.09
    çīĩåĪ»
    0.08
    å®ŀåĬ¡
    0.08
    é¹Ī
    0.08
    ä¸Ńä¿¡
    0.08
    Activations Density 0.022%

    No Known Activations