© 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. 54038
    Prev
    Next
    INDEX
    Explanations

    world premiere | display screens

    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
    æīĺ
    -0.11
    å¾µ
    -0.10
    icode
    -0.09
    å¼Ģä¼ļ
    -0.09
    oke
    -0.09
    itos
    -0.09
    æŀ
    -0.09
    ç®IJ
    -0.09
    packing
    -0.09
    æı´
    -0.09
    POSITIVE LOGITS
    éĿ¢åīį
    0.10
    çľĭè§ģ
    0.09
    åı¯è§ģ
    0.09
    ä¸ĸ人
    0.09
    contr
    0.09
    好çľĭçļĦ
    0.08
     anyone
    0.08
     contradiction
    0.08
    åħ¬å¼Ģ
    0.08
     anybody
    0.08
    Activations Density 0.042%

    No Known Activations