© 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. 37274
    Prev
    Next
    INDEX
    Explanations

    is followed by number

    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
    æĺ¯ä¸Ģ件
    -0.10
    è¿ĻæĶ¯
    -0.10
    éĤ£æ®µ
    -0.10
    è¿Ļ段
    -0.09
    éĺ¿æł¹
    -0.09
    è¿Ļäºĭ
    -0.09
    åŁºè°ĥ
    -0.09
    è¿Ļæĺ¯æĪij
    -0.09
    ä¸įå¿į
    -0.09
    樵
    -0.09
    POSITIVE LOGITS
    -fi
    0.10
    umper
    0.09
    æ·Į
    0.09
    -fly
    0.09
    åĢ¼å¾Ĺä¸Ģ
    0.09
    holding
    0.08
    rijk
    0.08
    .setInput
    0.08
    lington
    0.08
    xee
    0.08
    Activations Density 0.161%

    No Known Activations