© 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. 63286
    Prev
    Next
    INDEX
    Explanations

    Judaism and God

    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
    å¸ĸ
    -0.10
    eres
    -0.09
    çĨŁç»ĥ
    -0.08
    å®Ĺ
    -0.08
    éļĶ离
    -0.08
    åijĬ
    -0.08
     Wish
    -0.08
     TRACK
    -0.08
    zp
    -0.08
    æĭĵ
    -0.08
    POSITIVE LOGITS
    å³»
    0.10
    为ä»Ģä¹Īä¼ļ
    0.09
    æľ¬æĬ¥
    0.09
    éĽį
    0.09
    人人éĥ½
    0.09
    çļĦåĨħ容
    0.09
    éªĪ
    0.08
    eln
    0.08
     scor
    0.08
    SEQ
    0.08
    Activations Density 0.030%

    No Known Activations