© 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. 23835
    Prev
    Next
    INDEX
    Explanations

    GPU Compute

    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
    综åIJĪæĢ§
    -0.10
    èİ·è¯Ħ
    -0.09
    æµģæ°´
    -0.09
    ç³ĸå°¿
    -0.09
    赤
    -0.09
    èµĦäº§è´ŁåĢº
    -0.09
    妯
    -0.09
    ãģĦãĤĭ
    -0.08
    çŃ·åŃIJ
    -0.08
    éĥ¨ç½²
    -0.08
    POSITIVE LOGITS
    anne
    0.09
    ÙħÙĪر
    0.09
    fld
    0.08
    å¹³æŶ
    0.08
    å¾ģ
    0.08
    unj
    0.08
    æī§
    0.08
    aries
    0.08
    çķ¶çĦ¶
    0.07
    åıĮéĩį
    0.07
    Activations Density 0.168%

    No Known Activations