© 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. 36530
    Prev
    Next
    INDEX
    Explanations

    machineautomatedmachinesautomation

    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
    åĺĺ
    -0.10
    躬
    -0.09
    è¶Ł
    -0.09
    è¨Ģè¡Į
    -0.09
    åģļæ³ķ
    -0.08
    _LAYER
    -0.08
    è¦ģåģļ好
    -0.08
    åIJ¬çĿĢ
    -0.08
    ä¸īæĿ¡
    -0.08
    esen
    -0.08
    POSITIVE LOGITS
    èĩªåĬ¨åĮĸ
    0.23
    æľºåĻ¨
    0.20
     machines
    0.19
     automated
    0.18
     automation
    0.17
     Machines
    0.16
     machine
    0.16
    èĩªåĬ¨
    0.16
    æľºæ¢°åĮĸ
    0.16
    åħ¨èĩªåĬ¨
    0.16
    Activations Density 0.195%

    No Known Activations