© 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. 49708
    Prev
    Next
    INDEX
    Explanations

    automatically generating, opening, or sending

    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
    æѤåĪ»
    -0.11
    讯
    -0.10
    zilla
    -0.10
    .getService
    -0.09
    æļĤæŶ
    -0.09
    pone
    -0.09
    isor
    -0.09
    èģŀ
    -0.09
    åĨįä¸Ģ次
    -0.09
    ÙĪد
    -0.09
    POSITIVE LOGITS
    mente
    0.10
     automatically
    0.09
    çŃ¹
    0.09
    /manual
    0.09
    /auto
    0.09
    ìłģìľ¼ë¡ľ
    0.09
    aly
    0.09
    ìłģìĿ¸
    0.09
    ä¸īåĪĨ
    0.09
    çĽĺ
    0.08
    Activations Density 0.046%

    No Known Activations