© 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. 11833
    Prev
    Next
    INDEX
    Explanations

    civil war, city, illusion, love, opponents

    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
    æĹ©æĹ¥
    -0.09
    æĬĹæĹ¥
    -0.08
    Č
    -0.08
    屯
    -0.08
    åĬłä»¥
    -0.08
    æ¸ħé¦Ļ
    -0.07
    _java
    -0.07
    lg
    -0.07
    amp
    -0.07
     forth
    -0.07
    POSITIVE LOGITS
    æĹłç¼ĺ
    0.11
    éĵ¿
    0.10
    å¦į
    0.10
    åįĪé¥Ń
    0.10
    èĦĨ
    0.10
    à¹ĩà¸Ķ
    0.10
    shaw
    0.09
    å®ĺæĸ¹å¾®åįļ
    0.09
    è¾IJ
    0.09
    æļĦ
    0.09
    Activations Density 0.041%

    No Known Activations