© 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. 35440
    Prev
    Next
    INDEX
    Explanations

    numbers and roman numerals

    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
    è¾İ
    -0.09
    è¿ijè·Ŀ离
    -0.09
     ëĶ°
    -0.09
    èĪģ
    -0.09
    zo
    -0.09
    opal
    -0.09
    æģĻ
    -0.09
    ãģ°ãģĭãĤĬ
    -0.09
    å¿Ń
    -0.09
    ogan
    -0.08
    POSITIVE LOGITS
     Mud
    0.09
    è°ĥæݧ
    0.08
     ever
    0.08
    il
    0.08
    åŁİå¸Ĥ建设
    0.08
    å°±è¿Ļæł·
    0.08
    责任人
    0.08
    èĬĻèĵī
    0.08
    kest
    0.07
    åķ¸
    0.07
    Activations Density 0.564%

    No Known Activations