© 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. 51581
    Prev
    Next
    INDEX
    Explanations

    prevention and treatment

    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
    åıijæĮ¥
    -0.10
    éªIJ
    -0.09
    çķĻ
    -0.08
    çĻ¼æı®
    -0.08
    _PY
    -0.08
    жа
    -0.08
    ä¿Ł
    -0.08
    åIJĦè¡Į
    -0.08
    足
    -0.08
    åĢĶ
    -0.08
    POSITIVE LOGITS
    ì´Į
    0.10
    ä¸Ģ身
    0.09
    åħĪ导
    0.09
    ä¸į代表
    0.09
    ÑĢÑĥ
    0.09
    çªģåıijäºĭ件
    0.08
    æłŁ
    0.08
    èŁ²
    0.08
    AREN
    0.08
    侧
    0.08
    Activations Density 0.091%

    No Known Activations