© 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. 56415
    Prev
    Next
    INDEX
    Explanations

    transit station

    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
    æį
    -0.10
    æĹĹä¸ĭçļĦ
    -0.10
    CKER
    -0.09
    ä¸ĥæľĪ
    -0.09
    ä¸į顾
    -0.09
    èĩªè´Ł
    -0.09
    éģĵè·¯ä¸Ĭ
    -0.09
     infix
    -0.08
    éĢĭ
    -0.08
    ãĤ¯ãĥ©ãĥĸ
    -0.08
    POSITIVE LOGITS
    ANDOM
    0.10
    ç«ĻçĤ¹
    0.09
    交éĢļæŀ¢çº½
    0.09
    èĭĩ
    0.08
    ald
    0.08
    åĨ¯
    0.08
    cers
    0.08
    ç«Ļ
    0.08
     station
    0.08
     Whip
    0.08
    Activations Density 0.102%

    No Known Activations