© 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. 4969
    Prev
    Next
    INDEX
    Explanations

    loving renditions, clear timbre, sincerity, Revolutionary, Copyright, array, Simple

    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
    è¿Ļåıª
    -0.09
    è´±
    -0.09
    åħ®
    -0.09
    ooting
    -0.09
    èµŀç¾İ
    -0.08
    anson
    -0.08
     Once
    -0.08
    çĬ¯ç½ª
    -0.08
    éĶ»çĤ¼
    -0.08
    åį¿
    -0.08
    POSITIVE LOGITS
    å¤įæŁ¥
    0.09
    åIJ¬è¯Ŀ
    0.08
    寡
    0.08
    око
    0.08
    æĿ¾å¼Ľ
    0.08
    INU
    0.08
     bully
    0.08
    оÑī
    0.08
    åĬ¨åijĺ
    0.08
     паÑĢÑĤ
    0.08
    Activations Density 0.022%

    No Known Activations