© 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. 8201
    Prev
    Next
    INDEX
    Explanations

    confused

    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
    èŁł
    -0.09
    éĶ¢
    -0.09
    ä»»ä½ķæŶåĢĻ
    -0.09
    å·²ä¹ħ
    -0.09
    å¬Ĺ
    -0.09
    upro
    -0.09
     italia
    -0.08
    éĩįä¸Ńä¹ĭéĩį
    -0.08
    æľĢ大çļĦ
    -0.08
    ä¸Ģå¾ĭ
    -0.08
    POSITIVE LOGITS
    ìĶ©
    0.10
    ä¸į太
    0.10
    åIJĪ
    0.09
    æľīçĤ¹
    0.09
    对æĸ¹
    0.09
     комиÑģÑģи
    0.09
    éĥ½ä¼ļæľī
    0.08
    æľīä¸ĢçĤ¹
    0.08
    folio
    0.08
     Medium
    0.08
    Activations Density 0.110%

    No Known Activations