© 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. 36036
    Prev
    Next
    INDEX
    Explanations

    Christian faith and God's word

    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
    ç°¸
    -0.09
    ÙĥÙĬ
    -0.09
    被æīĵ
    -0.09
    çĹķ
    -0.08
    驳
    -0.08
    è¹Ń
    -0.08
    éĤ£æŶåĢĻ
    -0.08
     Platt
    -0.08
     chast
    -0.07
    çļĦä¸ľè¥¿
    -0.07
    POSITIVE LOGITS
    åħ³äºİæĪij们
    0.09
    ä¸Ģæīĭ
    0.09
    çī©ä»·
    0.09
    åijĬè¯īæĪij们
    0.09
     Offline
    0.09
    æĻ«
    0.09
    .ErrorCode
    0.08
    ilos
    0.08
    _softmax
    0.08
    agens
    0.08
    Activations Density 0.044%

    No Known Activations