© 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. 34928
    Prev
    Next
    INDEX
    Explanations

    duration of time

    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
    è¡¿
    -0.10
    åIJĦ个çݯèĬĤ
    -0.09
    è¿ĻéĩĮçļĦ
    -0.09
    èĦĤ
    -0.09
    å²IJ
    -0.09
    åģĩæĹ¥
    -0.09
    aos
    -0.09
    åIJİç»Ń
    -0.09
    è¥Ł
    -0.09
    portal
    -0.09
    POSITIVE LOGITS
    æľŁéĹ´
    0.24
    æľŁéĸĵ
    0.19
    è¿Ļ段æŶéĹ´
    0.16
    åħ¶éĹ´
    0.15
    æŶéĹ´åĨħ
    0.14
    æľŁåĨħ
    0.12
    çļĦæŶéĹ´éĩĮ
    0.11
    èĮĥåĽ´åĨħ
    0.11
    è¿Ļ段
    0.11
    è¿ĩç¨ĭä¸Ń
    0.11
    Activations Density 0.048%

    No Known Activations