© 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. 19829
    Prev
    Next
    INDEX
    Explanations

    followed by past events or discoveries

    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
    iona
    -0.09
    èĽ¾
    -0.08
    å¤ļå¹´æĿ¥
    -0.08
    ç³Ĭ
    -0.08
    forma
    -0.08
    å¤ĸæı´
    -0.08
    娥
    -0.08
     Sands
    -0.08
    ä¸ĩä¸Ģ
    -0.08
    èĨ»
    -0.08
    POSITIVE LOGITS
    åŃķèĤ²
    0.11
    æ°Ķ温
    0.10
    .mvc
    0.09
    æĤĦ
    0.09
    åħħæĸ¥
    0.09
    纲
    0.09
    ä½ŀ
    0.09
    贵宾
    0.09
    缮çĿ¹
    0.09
    éĩįè¦ģçļĦ
    0.09
    Activations Density 0.117%

    No Known Activations