© 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. 23342
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    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
    æĸ«
    -0.09
    æ¿Ĵ临
    -0.09
    IVA
    -0.08
    holm
    -0.08
    æ´¹
    -0.08
    çĻ»ä¸Ĭ
    -0.08
     çaÄŁ
    -0.08
    /big
    -0.08
     dotted
    -0.08
     bÃło
    -0.08
    POSITIVE LOGITS
    çī¹æ´¾
    0.10
    ä¸İåIJ¦
    0.10
    åĨįåĪ°
    0.10
    楣
    0.10
    åĴĮæĶ¯æĮģ
    0.10
    æĸ°å¼Ģ
    0.09
    .Automation
    0.08
    æľīåĪ©äºİ
    0.08
    .dp
    0.08
    èµ·åºĬ
    0.08
    Activations Density 0.178%

    No Known Activations