© 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. 20760
    Prev
    Next
    INDEX
    Explanations

    the so-called

    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
    olds
    -0.09
    ett
    -0.08
    æĬ½
    -0.08
     ÙĨÙĤ
    -0.08
    oubles
    -0.08
    ________________________________________________________________
    -0.08
    çĤ¹å¤ļ
    -0.08
     getS
    -0.08
    åľ°ä½į
    -0.08
    ength
    -0.07
    POSITIVE LOGITS
    称ä¹ĭ为
    0.17
    称为
    0.17
    被称为
    0.15
    åı«åģļ
    0.14
    è¿Ļå°±æĺ¯
    0.14
    ä¿Ĺ称
    0.14
    æīĢè°ĵçļĦ
    0.13
    æŀĦæĪIJäºĨ
    0.13
    æīĢè°ĵ
    0.13
    常说
    0.12
    Activations Density 0.570%

    No Known Activations