© 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. 2498
    Prev
    Next
    INDEX
    Explanations

    punctuations and separators

    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
    eler
    -0.11
    whose
    -0.10
    /be
    -0.10
    æĦı大
    -0.10
    å§Ĩ
    -0.09
    åħ¬åħ±æĸĩåĮĸ
    -0.09
    doi
    -0.09
    ä¹Łåıªæľī
    -0.09
    鼶åĶ®åķĨ
    -0.09
    otron
    -0.09
    POSITIVE LOGITS
    ä¹Łå°±æĺ¯è¯´
    0.15
    ä»Ģä¹ĪæĦıæĢĿ
    0.12
    inded
    0.10
    åį³
    0.09
    AIT
    0.09
    ãģ¤ãģ¾ãĤĬ
    0.09
    åĽłèĢĮ
    0.08
    ait
    0.08
    æĹ¢è¦ģ
    0.08
    -admin
    0.08
    Activations Density 0.236%

    No Known Activations