© 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. 28079
    Prev
    Next
    INDEX
    Explanations

    no compensation or contributions

    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
     scram
    -0.08
    _notifications
    -0.08
    êu
    -0.08
    æݾ
    -0.08
    åĤ¨èĵĦ
    -0.08
    åijĽ
    -0.08
    _pdf
    -0.08
    erk
    -0.08
     justified
    -0.08
    æĿ¡è¯Ħ论
    -0.08
    POSITIVE LOGITS
    æĹłå£°
    0.09
     Wrest
    0.09
    大çīĩ
    0.09
    æİ¥åıĹäºĨ
    0.09
    èµĦåĬ©
    0.09
    å°ıå¿ĥ
    0.09
    èĩ´åij½
    0.08
    éĴ¿
    0.08
    ä»ħ代表
    0.08
    ä»ĺè´¹
    0.08
    Activations Density 0.044%

    No Known Activations