© 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. 55106
    Prev
    Next
    INDEX
    Explanations

    pin and adapter interface

    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
    ubb
    -0.10
    occ
    -0.09
    辨
    -0.08
    akers
    -0.08
    LOSS
    -0.08
     tweaked
    -0.08
     Luz
    -0.08
    entries
    -0.08
    æģ¶
    -0.08
    unn
    -0.08
    POSITIVE LOGITS
    çł´è§£
    0.11
    æ¥Ķ
    0.10
    çĶ¨å·¥
    0.10
    è¶´åľ¨
    0.10
    æĭĨ
    0.10
    åĪĨæŀIJå¸Ī
    0.10
    æĪIJåĬŁçİĩ
    0.10
     маÑģÑĤеÑĢ
    0.09
    æĮĸæİĺ
    0.09
    è¿Ĥ
    0.09
    Activations Density 0.149%

    No Known Activations