© 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. 5881
    Prev
    Next
    INDEX
    Explanations

    business startup success

    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
    çĶŃ
    -0.10
    akers
    -0.10
    ãĤ¯ãĥ©ãĥĸ
    -0.09
    æĬ¬å¤´
    -0.09
    è·Łè¿Ľ
    -0.09
    ä¸ĢåIJij
    -0.09
    é¢Ħç®Ĺ
    -0.09
    æħ·æħ¨
    -0.09
    èħ¹
    -0.09
    ipsis
    -0.09
    POSITIVE LOGITS
    æĪIJç«ĭäºĨ
    0.11
    æĪIJç«ĭ
    0.10
    æĬĵ
    0.10
    åĪĽåĬŀ
    0.10
     founders
    0.09
    åĪĽç«ĭ
    0.09
    -founded
    0.09
    æĪIJç«ĭäºİ
    0.09
    UCH
    0.09
    çī©
    0.09
    Activations Density 0.129%

    No Known Activations