© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 35862
    Prev
    Next
    INDEX
    Explanations

    ranging from ... to

    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
    åħ¶ä»ĸçļĦ
    -0.10
    æIJı
    -0.10
    åĪĿè¡·
    -0.10
    åıĺ身
    -0.09
    åĸ½
    -0.09
    izz
    -0.09
    éĤ£ä¸ĢåĪ»
    -0.09
    è¿Ļ座åŁİå¸Ĥ
    -0.09
    ä¸įæĸŃå¢ŀ强
    -0.09
    éºĤ
    -0.09
    POSITIVE LOGITS
    åΰ
    0.10
    ä»İäºĭ
    0.10
    åΰæľĢåIJİ
    0.09
    åĨįåΰ
    0.08
    imon
    0.08
    åΰäºĨ
    0.08
    Literal
    0.08
    UTH
    0.08
    fully
    0.08
     Rwanda
    0.07
    Activations Density 0.053%

    No Known Activations