© 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. 19268
    Prev
    Next
    INDEX
    Explanations

    att wireless service

    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¬å®īå±Ģ
    -0.10
    é¼ĭ
    -0.09
    çķĻè¨Ģ
    -0.09
    ä¸ĭ乡
    -0.09
     дÑĥÑħ
    -0.09
    èĭ
    -0.09
    åIJĮè¡Į
    -0.09
    åĬ¨æľº
    -0.09
    iley
    -0.08
    Devices
    -0.08
    POSITIVE LOGITS
    å¼Ģåĩº
    0.12
    åŁ¹
    0.08
    çĩĥ
    0.08
    港åı£
    0.08
    æĥ¶
    0.08
    adder
    0.08
    è¿IJè´¹
    0.08
    æĪ¢
    0.08
    ichte
    0.08
    æIJº
    0.08
    Activations Density 0.013%

    No Known Activations