© 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. 33716
    Prev
    Next
    INDEX
    Explanations

    waiting for

    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
    ái
    -0.09
    .sd
    -0.09
    ries
    -0.09
    arium
    -0.09
    _expect
    -0.09
    åı¥è¯Ŀ
    -0.08
    ä¾£
    -0.08
    .expect
    -0.08
    MEA
    -0.08
    åľ°ä½į
    -0.08
    POSITIVE LOGITS
    ç°Į
    0.10
     ведÑĮ
    0.10
    ä¸ĭæīĭ
    0.09
    鹫
    0.09
    ä¸ĸä¿Ĺ
    0.09
    æł¼å°Ķ
    0.09
    åĽłèĢĮ
    0.09
    ä½ĵä¼ļåĪ°
    0.08
    以èĩ´
    0.08
    anio
    0.08
    Activations Density 0.005%

    No Known Activations