© 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. 18554
    Prev
    Next
    INDEX
    Explanations

    common descriptive phrases

    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
    ook
    -0.09
    èĥ½å¤Łè®©
    -0.09
    chu
    -0.09
    æĬļæij¸
    -0.09
    éĥ½æľīçĿĢ
    -0.09
    åİ¢
    -0.09
    妻åŃIJ
    -0.08
     Rig
    -0.08
    æģ¶
    -0.08
    è¯ķçĿĢ
    -0.08
    POSITIVE LOGITS
    å¤ļäºĨ
    0.10
    åı¯è°ĵ
    0.10
    åĵī
    0.09
    éļ¾æĢª
    0.09
    æĿ¯
    0.09
    åĻ«
    0.09
    .lst
    0.08
    åŃ°
    0.08
    è§ĨåIJ¬
    0.08
    иÑĩно
    0.08
    Activations Density 0.055%

    No Known Activations