© 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. 5656
    Prev
    Next
    INDEX
    Explanations

    peer review process

    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
    ç»ĩ
    -0.09
    绣
    -0.09
     uncont
    -0.09
    çŀ»
    -0.09
    prises
    -0.09
    indle
    -0.09
    ofil
    -0.08
     leg
    -0.08
    OMET
    -0.08
    ToFile
    -0.08
    POSITIVE LOGITS
    è¿ĩçļĦ
    0.10
    æł¡å¤ĸ
    0.10
    两个å°ıæŶ
    0.10
    ainer
    0.10
    sgi
    0.09
    snake
    0.09
    è¿ĩå¾Ĺ
    0.09
    éĥ¨ä¸»ä»»
    0.09
    åij³éģĵ
    0.09
    åįıä¼ļä¼ļéķ¿
    0.09
    Activations Density 0.047%

    No Known Activations