© 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. 37033
    Prev
    Next
    INDEX
    Explanations

    copyrights and protection

    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
    bo
    -0.09
    çķĮ
    -0.09
    离å¼ĢäºĨ
    -0.09
    åł¡
    -0.08
    BO
    -0.08
    åħ¶æ¬¡æĺ¯
    -0.08
     bo
    -0.08
     Buff
    -0.08
    å¾ĭ
    -0.08
    çIJı
    -0.08
    POSITIVE LOGITS
    ç¥IJ
    0.10
    enties
    0.10
    ç»´æĿĥ
    0.10
    åı¯æĢľ
    0.09
    Storm
    0.09
    ä»ĭè´¨
    0.09
    èĭĺ
    0.09
    amba
    0.09
    ä¸įåĥı
    0.09
    PRI
    0.08
    Activations Density 0.032%

    No Known Activations