© 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. 57165
    Prev
    Next
    INDEX
    Explanations

    words ending in ers or ors

    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
    -0.10
    ç´°
    -0.09
    ç»ĨèĬĤ
    -0.09
    带走
    -0.09
    _ctxt
    -0.09
    ansa
    -0.08
    碾
    -0.08
    æ·±å±Ĥ
    -0.08
    ä¸»æľº
    -0.08
    磾
    -0.08
    POSITIVE LOGITS
     Wand
    0.10
     thai
    0.10
    èįī
    0.09
    å·¥ç¨ĭæĸ½å·¥
    0.09
    æĮ¥
    0.09
    æĬ½
    0.09
    agos
    0.08
    roman
    0.08
    èĩªçĶ±
    0.08
    åħ¬æ°ij
    0.08
    Activations Density 0.015%

    No Known Activations