© 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. 33591
    Prev
    Next
    INDEX
    Explanations

    Partner, Director, Principal titles

    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
    顺
    -0.09
    é£İ鼨
    -0.09
    sequential
    -0.08
    åIJĪæł¼
    -0.08
    <TResult
    -0.08
    麻çĹ¹
    -0.08
     Bang
    -0.08
     اÙĦداخÙĦ
    -0.08
    åħħ足çļĦ
    -0.08
    ä¸ĵä¸ļä»İäºĭ
    -0.08
    POSITIVE LOGITS
    å®ŀäºĭ
    0.09
    åıĬ以ä¸Ĭ
    0.09
    avic
    0.09
    ×Ļת
    0.09
    åįĹå±±
    0.09
    LEE
    0.09
    -level
    0.08
    iol
    0.08
    egin
    0.08
     Lair
    0.08
    Activations Density 0.019%

    No Known Activations