© 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. 19239
    Prev
    Next
    INDEX
    Explanations

    job titles

    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
    åIJĮäºĭ们
    -0.10
    åIJĮä»ģ
    -0.09
    itar
    -0.09
    主管éĥ¨éŨ
    -0.09
    ä¸Ģçĵ¶
    -0.08
    å¼ĢæĶ¯
    -0.08
    å¨ĺ家
    -0.08
    ä¸Ĭåı¸
    -0.08
    管çIJĨå±Ĥ
    -0.08
    漫
    -0.08
    POSITIVE LOGITS
    导åIJij
    0.11
    ACHI
    0.09
    çĭİ
    0.09
    ANDING
    0.09
    (java
    0.08
    å¸ĥæĭī
    0.08
    _fit
    0.08
    ë°¤
    0.08
     Catalan
    0.08
    ser
    0.08
    Activations Density 0.088%

    No Known Activations