© 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. 48354
    Prev
    Next
    INDEX
    Explanations

    open to

    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
    orage
    -0.08
     liken
    -0.08
    ilit
    -0.08
    orrent
    -0.08
    æ´¾
    -0.08
    cient
    -0.08
    خب
    -0.08
    chod
    -0.08
    upal
    -0.08
    unal
    -0.08
    POSITIVE LOGITS
    鸵
    0.10
    ä¸Ńå¤ĸ
    0.10
    çŃ®
    0.09
    åľ¨å¤ĸ
    0.09
    ä»»ä½ķå½¢å¼ı
    0.09
    设æĸ½å»ºè®¾
    0.09
    ä»»ä½ķ
    0.09
    åħ¨åİ¿
    0.09
    广大群ä¼Ĺ
    0.09
    åIJĦè¡ĮåIJĦä¸ļ
    0.09
    Activations Density 0.009%

    No Known Activations