© 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. 20091
    Prev
    Next
    INDEX
    Explanations

    reflexive 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
    å¼ĵ
    -0.09
    æĹģ
    -0.09
    ä½ĵåĨħ
    -0.09
    çĻ½éĽª
    -0.08
    èIJ½ä¸ĭ
    -0.08
    éĹ²
    -0.08
    OrFail
    -0.08
    并åIJij
    -0.08
    ä¸įæĢķ
    -0.08
    èĢķèĢĺ
    -0.08
    POSITIVE LOGITS
    å®ŀæķĪ
    0.09
    ä¸Ģéĥ¨
    0.09
    ajs
    0.09
    Ļ
    0.09
    çĤ¯
    0.09
    ç®Ĺ
    0.08
    CORD
    0.08
    çī¢
    0.08
    æį¢æĿ¥
    0.08
    à¹Ģà¸Ńà¸ĩ
    0.08
    Activations Density 0.023%

    No Known Activations