© 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. 34244
    Prev
    Next
    INDEX
    Explanations

    for the most part

    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
    åĪ«äººçļĦ
    -0.11
    éªĬ
    -0.10
    岸边
    -0.09
    笥
    -0.09
    åĪ«äºº
    -0.09
    åģ»
    -0.08
    çªģçł´åı£
    -0.08
    rets
    -0.08
    é²ľæĺİ
    -0.08
    åħ¶å®ŀ
    -0.08
    POSITIVE LOGITS
    æĿ¥è¯´
    0.10
    ç»Ŀ大éĥ¨åĪĨ
    0.10
    æĿ¥è®²
    0.10
    大éĥ¨åĪĨ
    0.10
    못
    0.10
     largely
    0.09
     sake
    0.09
    pole
    0.09
    è¿ĺä¸įéĶĻ
    0.09
    ãģ¨ãģĦãģ£ãģ¦
    0.09
    Activations Density 0.029%

    No Known Activations