© 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. 20543
    Prev
    Next
    INDEX
    Explanations

    established followed by a noun

    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
    æĬ±
    -0.09
    çªĴ
    -0.09
    æģ¤
    -0.09
    è´¢ç¨İ
    -0.08
    aggi
    -0.08
    ound
    -0.08
    积æŀģå¼Ģå±ķ
    -0.08
    orial
    -0.08
    éļĻ
    -0.08
    ivate
    -0.08
    POSITIVE LOGITS
    å·²ä¹ħçļĦ
    0.13
     established
    0.12
    æĪIJçĨŁçļĦ
    0.11
    Establish
    0.11
    ment
    0.10
    è¿Ļæĺ¯åĽłä¸º
    0.10
    MENT
    0.10
    udies
    0.10
    ãĥ¡ãĥ³ãĥĪ
    0.10
     Established
    0.10
    Activations Density 0.022%

    No Known Activations