© 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. 7707
    Prev
    Next
    INDEX
    Explanations

    object manipulation methods

    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
    åħħå®ŀ
    -0.09
    å¯ĦãģĽ
    -0.08
     pound
    -0.08
    å®ŀæĥł
    -0.08
    æ´ĹåĩĢ
    -0.08
    анÑĤ
    -0.08
    IDS
    -0.08
    ITS
    -0.08
     Miz
    -0.08
    èħ¥
    -0.08
    POSITIVE LOGITS
    è°Īèµ·
    0.10
    çī¹çĤ¹æĺ¯
    0.09
    .ci
    0.09
    主页
    0.09
    éķ¦
    0.09
    å¼ŁåŃIJ
    0.09
    lpVtbl
    0.09
     Wen
    0.08
    åħ¬çĽĬæĢ§
    0.08
    èĢģåĮĸ
    0.08
    Activations Density 1.473%

    No Known Activations