© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19873
    Prev
    Next
    INDEX
    Explanations

    covered by or under

    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
    æ¸
    -0.12
    éģ¨
    -0.10
    åŀĴ
    -0.10
    大人
    -0.10
    achable
    -0.09
    大æĪĺ
    -0.09
    èĩªèº«
    -0.09
    äºĶéĩij
    -0.09
    éļľç¢į
    -0.09
    çļĦæĪIJéķ¿
    -0.09
    POSITIVE LOGITS
    纳åħ¥
    0.14
     covered
    0.10
     included
    0.10
     Covered
    0.09
    covered
    0.09
    ä¸įåľ¨
    0.09
    9
    0.09
    åľ¨åĨħçļĦ
    0.09
    kit
    0.08
    3
    0.08
    Activations Density 0.105%

    No Known Activations