© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8715
    Prev
    Next
    INDEX
    Explanations

    everything you need

    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
    ners
    -0.08
    çī¹æĿĥ
    -0.08
    azel
    -0.08
    ä¾£
    -0.08
    æıŃ
    -0.08
    èĩªåľ¨
    -0.08
     sidel
    -0.08
    3
    -0.07
    ç»Ŀ
    -0.07
    åŃĽ
    -0.07
    POSITIVE LOGITS
    é½IJ
    0.11
    åį´åıĪ
    0.10
    æĹ¥å¸¸
    0.10
    便åĪ©
    0.10
    çĽħ
    0.10
    å®Įå¤ĩ
    0.10
    佬
    0.09
    ква
    0.09
    åıĸèĥľ
    0.09
    åĪĩ
    0.09
    Activations Density 0.024%

    No Known Activations