© 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. 52077
    Prev
    Next
    INDEX
    Explanations

    issues and alerts

    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
    å»ĵ
    -0.10
    è§ģè¿ĩ
    -0.09
    èij¡èIJĦ
    -0.08
    å¾¹
    -0.08
    äºĶåĽĽ
    -0.08
    åģ·
    -0.08
    -bel
    -0.08
    ç¥ŀéĢļ
    -0.08
    åĩ¤åĩ°
    -0.08
    è¢ģ
    -0.08
    POSITIVE LOGITS
    é¢ĦèѦ
    0.12
    èѦ
    0.12
    èŃ¦ç¤º
    0.10
    åĦĨ
    0.10
    æĬ¥èѦ
    0.09
    åijĪ
    0.09
    PILE
    0.09
    票
    0.09
    缴å±ŀ
    0.09
    æĮŁ
    0.09
    Activations Density 0.070%

    No Known Activations