© 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. 3506
    Prev
    Next
    INDEX
    Explanations

    as a result

    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
    åģļ大
    -0.10
    ä¸į解
    -0.09
    æ¿ł
    -0.09
    eld
    -0.09
    åĴĦ
    -0.09
    ukan
    -0.09
    为æĤ¨
    -0.08
     ÑĢеализаÑĨи
    -0.08
    åĪ°è¿ĻéĩĮ
    -0.08
    è¯ķçĿĢ
    -0.08
    POSITIVE LOGITS
    ä¹İ
    0.10
    UNCH
    0.10
    å°±æľīäºĨ
    0.09
    iem
    0.09
    尽管
    0.09
    åı¯ä»¥èİ·å¾Ĺ
    0.09
    oth
    0.09
    uelle
    0.08
    ä¸Ģ大æī¹
    0.08
    åĨ²
    0.08
    Activations Density 0.035%

    No Known Activations