© 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. 39619
    Prev
    Next
    INDEX
    Explanations

    authority or management

    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
    pb
    -0.10
    pu
    -0.09
    ä¼ĺå¼Ĥ
    -0.08
    ä¼ĺç§ĢçļĦ
    -0.08
    ứng
    -0.08
    FileSystem
    -0.08
    äººåľ¨
    -0.08
    pcs
    -0.08
     decor
    -0.08
    Decor
    -0.08
    POSITIVE LOGITS
    主管éĥ¨éŨ
    0.10
    å½ĵå±Ģ
    0.10
     Authorities
    0.10
    管çIJĨéĥ¨éŨ
    0.10
    羸
    0.09
    梦幻
    0.09
    åIJĦè¡Į
    0.09
    å½ĵåľ°æĶ¿åºľ
    0.09
     authorities
    0.09
    è¶Ł
    0.09
    Activations Density 0.107%

    No Known Activations