© 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. 22970
    Prev
    Next
    INDEX
    Explanations

    role in relationships and systems

    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
    ä»ĵ
    -0.09
    侨
    -0.09
    å°ıçĶ·åŃ©
    -0.08
    ju
    -0.08
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.08
    ä¸Ģ缴å¤Ħäºİ
    -0.08
    ç§ķ
    -0.07
    éĻįåĪ°
    -0.07
     tertiary
    -0.07
    å¿Ĺ强
    -0.07
    POSITIVE LOGITS
    顾客
    0.10
    ç¿¡ç¿ł
    0.09
    .biz
    0.09
    orable
    0.09
    çħľ
    0.09
    irk
    0.09
    sal
    0.09
    èĪĮå°ĸ
    0.09
    foundland
    0.09
    WebKit
    0.09
    Activations Density 0.359%

    No Known Activations