© 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. 32042
    Prev
    Next
    INDEX
    Explanations

    U.S. state abbreviations

    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
     Cra
    -0.09
    quin
    -0.08
    çĮĹ
    -0.08
    çĸ¹
    -0.08
    견
    -0.08
    yal
    -0.08
    åŀĭä¼ģä¸ļ
    -0.08
    ongs
    -0.08
    éĽĮ
    -0.08
    é¢Ħè§ģ
    -0.08
    POSITIVE LOGITS
    å±İ
    0.09
    èį£èªī
    0.09
    ä»Ĭ
    0.09
    åİŁæĿ¥æĺ¯
    0.09
    å´ĩ
    0.09
    ฯ
    0.08
    Ñģид
    0.08
    èĶ¸
    0.08
    aire
    0.08
    佶
    0.08
    Activations Density 0.008%

    No Known Activations