© 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. 62685
    Prev
    Next
    INDEX
    Explanations

    western cowboy outlaw pioneer

    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
    åĨ¬å¥¥
    -0.10
    _AES
    -0.09
    èļģ
    -0.09
    çģ¯çģ«
    -0.09
    reeNode
    -0.09
    äºĶä¸Ģ
    -0.09
    _placement
    -0.08
    éĥ½å¸Ĥ
    -0.08
    åįıå®ļ
    -0.08
    èĪ°éĺŁ
    -0.08
    POSITIVE LOGITS
    åºŁ
    0.09
    åľª
    0.09
    ä¾ł
    0.09
     Wyoming
    0.09
    åħ°å·ŀ
    0.09
    ä¿Ŀ湿
    0.09
    æ´ĹèĦ¸
    0.09
    jeta
    0.09
    yers
    0.08
    éķĸ
    0.08
    Activations Density 0.028%

    No Known Activations