© 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. 2761
    Prev
    Next
    INDEX
    Explanations

    member of the

    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
    çIJĨå·¥
    -0.11
    iting
    -0.09
    ä¸Ģçķª
    -0.09
    缮åħī
    -0.09
    ece
    -0.09
    ocking
    -0.09
    æĦ¿
    -0.09
    åĪºæ¿Ģ
    -0.09
    åĽ¾è¡¨
    -0.08
    çľ¼åħī
    -0.08
    POSITIVE LOGITS
    SHA
    0.09
    SOR
    0.09
     Sug
    0.09
    åľ°éĿ¢
    0.09
     NIL
    0.08
     Wick
    0.08
    å¡ŀ
    0.08
    å¤ĩ
    0.08
     extrem
    0.08
    nex
    0.07
    Activations Density 0.054%

    No Known Activations