© 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. 18712
    Prev
    Next
    INDEX
    Explanations

    retired professions and roles

    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
    ities
    -0.10
    ERA
    -0.09
    ilder
    -0.09
    ny
    -0.09
    ReadStream
    -0.08
    eler
    -0.08
    缴èIJ¥
    -0.08
    ç¼ij
    -0.08
    硬åĮĸ
    -0.08
     Peg
    -0.08
    POSITIVE LOGITS
    èĩ³ä»Ĭ
    0.09
    ona
    0.09
    -secondary
    0.09
    å¤ļå¹´çļĦ
    0.09
     undefeated
    0.08
    ï¸
    0.08
    ä¸ĭæĿ¥çļĦ
    0.08
    WithError
    0.08
     khá»ıi
    0.08
    åīįæīĢ
    0.08
    Activations Density 0.011%

    No Known Activations