© 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. 36629
    Prev
    Next
    INDEX
    Explanations

    as written, as published, as seen, as passed

    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
    Harness
    -0.09
     bay
    -0.09
    åıijåĬ¨
    -0.09
    ä¹ĺ客
    -0.08
    ç¬ijçĿĢ
    -0.08
    chsel
    -0.08
    _CSR
    -0.08
    çĬĢ
    -0.08
    太è¿ĩ
    -0.08
    毫
    -0.08
    POSITIVE LOGITS
    æĿĮ
    0.09
    epend
    0.09
    eton
    0.08
    天天
    0.08
    æĸĩç§ij
    0.08
    ä¼¼ä¹İ
    0.08
     каз
    0.08
    çĸµ
    0.08
    æ±Łæ¹ĸ
    0.08
    åĩºçĤī
    0.08
    Activations Density 0.109%

    No Known Activations