© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20691
    Prev
    Next
    INDEX
    Explanations

    recent events or reports

    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
    常年
    -0.12
    çĵ¯
    -0.09
    äºĮåįģå¹´
    -0.09
    hurst
    -0.09
    azole
    -0.09
    åĩłå¹´
    -0.09
    æŶ任
    -0.09
    éĤ£æŶåĢĻ
    -0.08
     Fle
    -0.08
    èĸ¯
    -0.08
    POSITIVE LOGITS
    æĺ¨æĻļ
    0.10
     yesterday
    0.10
    æ·±å¤ľ
    0.10
    æľĢæĸ°çļĦ
    0.09
    æľĢæĸ°
    0.09
    常å§Ķ
    0.09
    æĺ¨å¤©
    0.09
    åij¨æľ«
    0.09
    è¨Ģè¡Į
    0.09
    æĺ¨æĹ¥
    0.09
    Activations Density 0.225%

    No Known Activations