© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22218
    Prev
    Next
    INDEX
    Explanations

    public utilities commission

    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
    大æĸ¹
    -0.10
    è¾ķ
    -0.09
     Mans
    -0.09
    ç²¾ç¾İ
    -0.09
    è¿Ļä¸Ģ次
    -0.08
     ÑģоÑĤ
    -0.08
    çĹ¢
    -0.08
    è±¹
    -0.08
    äºĮçĻ¾
    -0.08
     HISTORY
    -0.08
    POSITIVE LOGITS
    æ±
    0.09
    å¥
    0.09
    æľįåĬ¡æľºæŀĦ
    0.09
    è¹ij
    0.09
    èİİ
    0.09
    istrate
    0.08
    ãĤ¦ãĤ£
    0.08
    詹
    0.08
    çķĮçļĦ
    0.08
    éĢłèĪ¹
    0.08
    Activations Density 0.131%

    No Known Activations