© 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. 11196
    Prev
    Next
    INDEX
    Explanations

    thanks for

    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
    éĿł
    -0.10
     ÑģобиÑĢа
    -0.09
    ä¸į论æĺ¯
    -0.09
    ä¸Ģçľĭ
    -0.09
    ãģ¾ãģ¾
    -0.09
     Rou
    -0.08
     Conway
    -0.08
    MENT
    -0.08
    æīĢåľ¨
    -0.08
    以便
    -0.08
    POSITIVE LOGITS
    è¹Ĥ
    0.09
    edom
    0.08
    çļĦä¸ĢåĪĩ
    0.08
    åIJĮåŁİ
    0.08
     assistance
    0.08
    åĬłåĢį
    0.08
    estyle
    0.08
    çļĦ帮åĬ©
    0.08
    osh
    0.08
    apg
    0.08
    Activations Density 0.025%

    No Known Activations