© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20092
    Prev
    Next
    INDEX
    Explanations

    relative pronouns and determiners

    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
    çīĮ
    -0.10
    åħ¶æīĢ
    -0.10
    èħĭ
    -0.10
    罨
    -0.10
    ä¾ĿçĦ¶æĺ¯
    -0.09
    缮çļĦæĺ¯
    -0.09
    å¨ĺå¨ĺ
    -0.09
    ease
    -0.09
    å®ĥæĺ¯
    -0.09
    ç£Ļ
    -0.09
    POSITIVE LOGITS
    带头
    0.09
     chứ
    0.08
    OrNull
    0.08
    pir
    0.08
     cro
    0.08
     tipped
    0.08
     jerk
    0.08
    ç¨Ģ
    0.08
    éĢĴ
    0.08
     Relief
    0.08
    Activations Density 0.030%

    No Known Activations