© 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. 9148
    Prev
    Next
    INDEX
    Explanations

    a followed by nouns

    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
    èIJį
    -0.10
    è¯Ŀ
    -0.09
    SYM
    -0.09
    æŶéĹ´åĴĮ
    -0.09
    stops
    -0.09
    äºĨåIJĹ
    -0.08
    Indented
    -0.08
    rit
    -0.08
    çĥ§
    -0.08
    è£ģåĪ¤
    -0.08
    POSITIVE LOGITS
    ãģ¾ãģĹãģ¦
    0.10
    ä¸Ģ款
    0.10
    ä¸Ģéģĵ
    0.09
    æ··åIJĪ
    0.09
    ä¸Ģæŀ¶
    0.09
    ä¸Ģç¬Ķ
    0.08
    ä¸Ģ種
    0.08
    ãģŁãģı
    0.08
    ä¸ĢæĿ¡
    0.08
    ç±»åŀĭçļĦ
    0.08
    Activations Density 0.312%

    No Known Activations