© 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. 56550
    Prev
    Next
    INDEX
    Explanations

    the first time

    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
    骶
    -0.10
    è´¤
    -0.09
    åħ³äºİæĪij们
    -0.08
    å«¡
    -0.08
    çĬģ
    -0.08
    udder
    -0.08
    åIJĮæŶè¿ĺ
    -0.08
    ä»Ģä¹Īåı«
    -0.08
    ç¸
    -0.08
    pus
    -0.08
    POSITIVE LOGITS
    èijĨ
    0.10
     occasion
    0.09
    empo
    0.09
    تد
    0.09
    åıĤ
    0.09
     offen
    0.09
    æľīæľº
    0.08
    æĪijå¸Ĥ
    0.08
    竦
    0.08
    éo
    0.08
    Activations Density 0.031%

    No Known Activations