© 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. 7899
    Prev
    Next
    INDEX
    Explanations

    assembly reference

    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
    èįª
    -0.10
     ÑĢазвива
    -0.09
    å¼ĢéŨ
    -0.09
    åŀĤ
    -0.09
    óng
    -0.09
    æķ²
    -0.09
    çķ¸å½¢
    -0.08
    )NULL
    -0.08
    OSC
    -0.08
    å±Ģéĥ¨
    -0.08
    POSITIVE LOGITS
    é«ĺåİĭ
    0.10
    (classes
    0.10
    /classes
    0.09
    ä¸īåĽ½
    0.09
    æ·Ģ
    0.09
    classes
    0.09
    åįļçī©é¦Ĩ
    0.09
    Classes
    0.08
    æĹłå£°
    0.08
     classes
    0.08
    Activations Density 1.153%

    No Known Activations