© 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. 47991
    Prev
    Next
    INDEX
    Explanations

    HTML tags and attributes (`<a href=`, `class=`, `<b>`, `<em>`, `<code>`)

    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
    èİ«
    -0.10
    èĥ¼
    -0.10
     INCLUDED
    -0.10
    urally
    -0.10
    Ãłng
    -0.09
     Enumerator
    -0.09
    æµ´
    -0.09
    åıĻ
    -0.09
     ìĸ´ëĸ
    -0.09
    avi
    -0.09
    POSITIVE LOGITS
    çľĭä¸įè§ģ
    0.09
    å°±å¤ŁäºĨ
    0.08
    çĮĬ
    0.08
    ä¸ĢçĤ¹çĤ¹
    0.08
    ä¸į容
    0.08
     premise
    0.08
     WCS
    0.08
     Mits
    0.07
    å¾Īå°ı
    0.07
    ä¸ĺ
    0.07
    Activations Density 0.578%

    No Known Activations