© 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. 63035
    Prev
    Next
    INDEX
    Explanations

    activities and events

    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
    è°Ĺ
    -0.10
    åıĮåıĮ
    -0.09
    é«ĺå³°
    -0.09
    ä¸ĢæŶ
    -0.09
    解æĶ¾
    -0.08
    å¼Ģåħ·
    -0.08
    éĿ¢ç§¯çº¦
    -0.08
    延误
    -0.08
    åħļçļĦé¢Ĩ导
    -0.08
    yps
    -0.08
    POSITIVE LOGITS
     activities
    0.16
    丰å¯Įå¤ļ彩
    0.15
    æ´»åĬ¨
    0.15
    ä¸Ģç³»åĪĹ
    0.14
    æ´»åĭķ
    0.14
    ç³»åĪĹæ´»åĬ¨
    0.13
    å®£ä¼łæ´»åĬ¨
    0.13
     Activities
    0.13
    activities
    0.13
    äºĨä¸Ģç³»åĪĹ
    0.13
    Activations Density 0.070%

    No Known Activations