© 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. 56778
    Prev
    Next
    INDEX
    Explanations

    question words followed by pronouns

    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
     casual
    -0.10
    åĵĩ
    -0.09
    ä¸Ģå¥Ĺ
    -0.09
    IService
    -0.08
     ва
    -0.08
    è¿Ļå¥Ĺ
    -0.08
    æľīçĶ¨çļĦ
    -0.08
    æľĢæĹ©çļĦ
    -0.08
    çĶŁæ´»çļĦ
    -0.08
    楸
    -0.08
    POSITIVE LOGITS
    è°ĥéħį
    0.11
    æĺ¯åIJ¦ä¼ļ
    0.11
    omat
    0.10
     æĺ¯åIJ¦
    0.10
    æĺ¯åIJ¦
    0.10
    åı¯èĥ½åıijçĶŁ
    0.09
    è°ĥ
    0.09
    å¾Ĺèµ·
    0.09
     whether
    0.09
    èĪįå¾Ĺ
    0.09
    Activations Density 0.009%

    No Known Activations