© 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. 57439
    Prev
    Next
    INDEX
    Explanations

    food products consumer growth cure times

    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
    è¿ŀ
    -0.09
    æĦıå¿Ĺ
    -0.08
    ingo
    -0.08
    ableView
    -0.08
    ÙĤØ©
    -0.08
     needless
    -0.08
    éĨ®
    -0.08
    igin
    -0.08
    Fade
    -0.08
    <![
    -0.08
    POSITIVE LOGITS
    æķĪåĬĽ
    0.10
    éķ¿ä¹ħ
    0.10
    åĬ©åѦ
    0.10
    绦
    0.10
    èĢ½è¯¯
    0.09
    该æ¡Ī
    0.09
    åįĬ个å°ıæŶ
    0.09
    åľ®
    0.09
    æ£ĢéªĮ
    0.09
    éķĤ
    0.09
    Activations Density 0.245%

    No Known Activations