© 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. 55033
    Prev
    Next
    INDEX
    Explanations

    winner or winning

    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
     cue
    -0.08
     strugg
    -0.08
    iju
    -0.08
    æ¼ı
    -0.08
    .cat
    -0.08
    缮
    -0.08
    欹
    -0.08
    æĮ£
    -0.08
    ople
    -0.08
    å«Į
    -0.08
    POSITIVE LOGITS
    æģ¯æģ¯
    0.10
    èĢħçļĦ
    0.10
    æł¼å°Ķ
    0.09
    æĵħéķ¿
    0.09
    ç»Ī
    0.08
    ests
    0.08
    è´Ŀ壳
    0.08
    åĪĨ管
    0.08
    è´¶
    0.08
    æı½
    0.08
    Activations Density 0.031%

    No Known Activations