© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9287
    Prev
    Next
    INDEX
    Explanations

    the + capitalized noun

    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
    大èĥĨ
    -0.09
    çļĦæĦŁæĥħ
    -0.09
    acho
    -0.08
    è¯ģ
    -0.08
    å°¼äºļ
    -0.08
    itle
    -0.08
    orno
    -0.08
    åĪ¶æĪIJ
    -0.08
    çĶŁåĬ¨
    -0.08
    ros
    -0.08
    POSITIVE LOGITS
    ofil
    0.10
    åĩĿ
    0.09
    ophil
    0.08
    éĴĿ
    0.08
    é«
    0.08
    棼
    0.08
     bè
    0.08
    -grand
    0.08
    åĩĮæĻ¨
    0.08
    å¹¿æ³ĽåºĶçĶ¨
    0.08
    Activations Density 0.061%

    No Known Activations