© 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. 33460
    Prev
    Next
    INDEX
    Explanations

    take it by the edges

    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
    并åıijçĹĩ
    -0.11
    èµ·æĿ¥äºĨ
    -0.10
    ä¿Ĺè¯Ŀ说
    -0.10
    绫
    -0.10
    åľ¨ä»ĸçļĦ
    -0.10
    çĨ¨
    -0.10
     proper
    -0.09
    éĩĿ
    -0.09
    ponder
    -0.08
    achs
    -0.08
    POSITIVE LOGITS
    åį«
    0.10
    .places
    0.09
    æĮ¹
    0.09
    orest
    0.08
    ored
    0.08
     gez
    0.08
    ä¸ŃéĢĶ
    0.08
    æīŀ
    0.08
     Bea
    0.08
     Gerald
    0.08
    Activations Density 0.055%

    No Known Activations