© 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. 32946
    Prev
    Next
    INDEX
    Explanations

    experience

    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
    追溯
    -0.10
    éļ¨æĻĤ
    -0.09
    éļıæŶ
    -0.09
    窨
    -0.09
    åĵķ
    -0.09
    undef
    -0.09
    ä»įçĦ¶æĺ¯
    -0.09
    æ¡¡
    -0.09
    æ¡Ĥ
    -0.09
    è¯Ŀè¯Ń
    -0.09
    POSITIVE LOGITS
    ç»ıéªĮ
    0.18
     experience
    0.18
    çļĦç»ıéªĮ
    0.17
    å®ŀè·µç»ıéªĮ
    0.16
    ç¶ĵé©Ĺ
    0.16
    ç»ıéªĮåĴĮ
    0.15
     Experience
    0.15
    experience
    0.14
    å·¥ä½ľç»ıéªĮ
    0.14
    Experience
    0.13
    Activations Density 0.077%

    No Known Activations