© 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. 34428
    Prev
    Next
    INDEX
    Explanations

    nice, convenient, luxury

    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
    æķŀ
    -0.11
    ucks
    -0.10
    pers
    -0.09
    arf
    -0.09
    pell
    -0.08
    å¥ĩ迹
    -0.08
    /Page
    -0.08
    åĽłä¸ºå¥¹
    -0.08
    éĿ¢ä¸´çļĦ
    -0.08
     dõi
    -0.08
    POSITIVE LOGITS
    褡
    0.09
    âĻ¡
    0.09
    Canceled
    0.08
    мел
    0.08
    tons
    0.08
    textContent
    0.08
    меÑĤ
    0.08
    iliate
    0.08
    ons
    0.08
    sons
    0.08
    Activations Density 0.043%

    No Known Activations