© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22131
    Prev
    Next
    INDEX
    Explanations

    verter and converter

    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
    eman
    -0.09
    æļ´
    -0.09
    è°ĭ
    -0.09
    æµĭ
    -0.08
    wald
    -0.08
    çħ§
    -0.08
    èĮħ
    -0.08
    åij¨åĪĬ
    -0.08
     mult
    -0.08
    æĭĽèĤ¡
    -0.08
    POSITIVE LOGITS
     пÑĢаво
    0.10
    çĶŁæ´»çݯå¢ĥ
    0.10
    é²ľè¡Ģ
    0.10
    çĶŁæ´»æĸ¹å¼ı
    0.10
    æĸ°é²ľ
    0.10
    éļıå¤Ħ
    0.09
    大æĸ¹
    0.09
    梵
    0.09
    人æĢ§åĮĸ
    0.09
    ainer
    0.09
    Activations Density 0.239%

    No Known Activations