© 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. 53478
    Prev
    Next
    INDEX
    Explanations

    survival

    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
    irim
    -0.09
    wä
    -0.08
    æĹłå½¢
    -0.08
    åī©
    -0.08
    太å°ij
    -0.08
    صÙģ
    -0.08
    åŀĤ
    -0.08
    stry
    -0.08
    åĩĨåħ¥
    -0.08
    atura
    -0.08
    POSITIVE LOGITS
    åĴĮåıijå±ķ
    0.11
    ì±ħ
    0.11
    ä¹ĭéģĵ
    0.10
    主ä¹īèĢħ
    0.10
    ä¸İåıijå±ķ
    0.10
    -minded
    0.10
    ä¸Ģä¼ļ
    0.10
    éĶ¹
    0.09
    主ä¹īæĢĿæĥ³
    0.09
    主ä¹ī
    0.09
    Activations Density 0.019%

    No Known Activations