© 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. 11579
    Prev
    Next
    INDEX
    Explanations

    never more than

    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
    èĮĦ
    -0.10
    finity
    -0.10
    outh
    -0.10
    çĪµå£«
    -0.09
    ä¿ĿæĬ¤åĮº
    -0.09
    ä¸įå°½
    -0.09
    ä¸įèĥ½åĨį
    -0.09
    梯éĺŁ
    -0.09
    毫ä¸į
    -0.09
    åºŀ
    -0.09
    POSITIVE LOGITS
    ä¸Ģé¡¿
    0.09
    é¹Ĺ
    0.09
    çļĦä¸ĢéĿ¢
    0.08
    íģ¼
    0.08
     WHATSOEVER
    0.08
     whatsoever
    0.08
    è¿Ļæł·æīįèĥ½
    0.08
    theless
    0.08
    æĸ¹ä¾¿
    0.08
    egasus
    0.08
    Activations Density 0.023%

    No Known Activations