© 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. 8972
    Prev
    Next
    INDEX
    Explanations

    interesting thing

    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
    æķĻè®Ń
    -0.09
    è¿ĩåħ³
    -0.09
    èī°
    -0.09
    angan
    -0.09
    好å¤Ħ
    -0.09
    iane
    -0.08
    éłħ
    -0.08
    æģ¼
    -0.08
    好åIJĹ
    -0.08
    åĴ¯
    -0.08
    POSITIVE LOGITS
    ä»ĬåĽŀãģ¯
    0.09
    èİ«è¿ĩäºİ
    0.08
    agger
    0.08
    eno
    0.08
    asco
    0.08
     Guinness
    0.08
     ëĮĵ
    0.08
    enal
    0.08
    çļĦæĺ¯
    0.08
    fault
    0.08
    Activations Density 0.039%

    No Known Activations