© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5932
    Prev
    Next
    INDEX
    Explanations

    free agent decisions

    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
    blend
    -0.10
    èĢķèĢĺ
    -0.09
    erp
    -0.09
    赦
    -0.08
    çĽ¯
    -0.08
    _DL
    -0.08
    coal
    -0.08
    ç¥ĵ
    -0.08
    _tcb
    -0.08
     withdrawn
    -0.08
    POSITIVE LOGITS
    转ä¼ļ
    0.14
    离å¼Ģ
    0.14
    æĦıåIJij
    0.11
    å¿ĥ缮ä¸Ń
    0.11
    èĩªçĶ±
    0.11
    åįĸ家
    0.11
    éĽ¢éĸĭ
    0.10
    离å¼ĢäºĨ
    0.10
    转移åĪ°
    0.10
    è¿Ŀ约
    0.09
    Activations Density 0.104%

    No Known Activations