© 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. 32913
    Prev
    Next
    INDEX
    Explanations

    same

    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
    缨
    -0.10
    çīĪæĿĥå½Ĵ
    -0.10
    çĥ«
    -0.10
    åIJĥ饱
    -0.09
    äºĪ
    -0.09
    å¹³åĿĩæ°´å¹³
    -0.09
    æѧ
    -0.09
    طا
    -0.09
    lington
    -0.09
    irs
    -0.09
    POSITIVE LOGITS
    åľ¨åIJĮä¸Ģ
    0.15
    缸åIJĮçļĦ
    0.12
    åIJĮä¸Ģ
    0.11
    åIJĮä¸Ģ个
    0.11
    åĽºå®ļçļĦ
    0.11
    缸åIJĮ
    0.11
    éĿ¢åŃĶ
    0.10
    éĩįå¤į
    0.10
    æģĴ
    0.10
    åĽºå®ļ
    0.10
    Activations Density 0.060%

    No Known Activations