© 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. 57374
    Prev
    Next
    INDEX
    Explanations

    python scripts

    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
    楼梯
    -0.09
    åĬŀåħ¬å®¤
    -0.09
    sap
    -0.08
    è¿Ļä¸ĢåĪ»
    -0.08
    éĿ¢åħ·
    -0.08
    æĸĹ
    -0.08
     office
    -0.08
    åĩºåĽ½çķĻåѦ
    -0.08
    åĩºåı£
    -0.08
    igar
    -0.08
    POSITIVE LOGITS
     campground
    0.13
    èIJ¥åľ°
    0.12
    宿
    0.11
     кÑĢай
    0.10
    OTA
    0.10
     camping
    0.09
    æѧ
    0.09
    é«ĺå³°æľŁ
    0.09
     RV
    0.09
    /welcome
    0.09
    Activations Density 0.048%

    No Known Activations