© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37472
    Prev
    Next
    INDEX
    Explanations

    service and services

    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
    åĶ¯ä¸ĢçļĦ
    -0.09
    樵
    -0.08
    æµģè¡ĮçļĦ
    -0.08
    .Conn
    -0.08
     Lomb
    -0.08
    没æľīä»Ģä¹Ī
    -0.08
    áºŃp
    -0.08
    åĵĦ
    -0.08
    èĥ¼
    -0.08
    iedo
    -0.08
    POSITIVE LOGITS
    ukes
    0.10
    åħ±æľī
    0.09
    çļĦæĪIJåĬŁ
    0.09
    á»įng
    0.09
    æĸ¹ä¾¿
    0.09
    éĹ´çļĦ
    0.09
    åĬ©éķ¿
    0.09
    ä¿£
    0.09
     Abrams
    0.08
    eer
    0.08
    Activations Density 0.043%

    No Known Activations