© 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. 17438
    Prev
    Next
    INDEX
    Explanations

    server log information

    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
    çļĦåģļæ³ķ
    -0.09
    顺åĬ¿
    -0.09
    è´§å¸ģ
    -0.08
    okie
    -0.08
    ç»´å°Ķ
    -0.08
    å¤Ħäºİ
    -0.08
    æĪİ
    -0.08
    ä¾ĥ
    -0.08
    åĸ»
    -0.08
    è¿Ļä¹Īåģļ
    -0.08
    POSITIVE LOGITS
    çļĦæĹ¥
    0.12
    ãģĮåĩº
    0.10
    è¯ĬæĸŃ
    0.10
    èĦ¸èī²
    0.10
    è°ĥè¯ķ
    0.09
     logs
    0.09
    æĬ±æĢ¨
    0.09
    æĹ¥
    0.09
     debug
    0.09
    çĹĩçĬ¶
    0.09
    Activations Density 0.431%

    No Known Activations