© 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. 20898
    Prev
    Next
    INDEX
    Explanations

    one or two

    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
    é³ĸ
    -0.10
    èŀ¯
    -0.09
    ows
    -0.08
    笳
    -0.08
    undy
    -0.08
    ç«ł
    -0.08
    XL
    -0.08
    大å§IJ
    -0.08
    å¤įåIJĪ
    -0.07
    ãģªãģĭ
    -0.07
    POSITIVE LOGITS
    äºĮèĢħ
    0.19
    两èĢħ
    0.17
    è¿ĻäºĽä¸ľè¥¿
    0.13
    åīįèĢħ
    0.11
    åIJİèĢħ
    0.10
    ä¸Ĭè°ĥ
    0.09
    icont
    0.09
    æŀģ端
    0.09
    å±Ĭæ¯ķä¸ļçĶŁ
    0.09
     extremes
    0.09
    Activations Density 0.091%

    No Known Activations