© 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. 8360
    Prev
    Next
    INDEX
    Explanations

    pledge to

    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
    aceous
    -0.09
    æĶ¿çŃĸæݪæĸ½
    -0.09
    ially
    -0.09
    illation
    -0.08
    -minded
    -0.08
    åŃ¦å®¶
    -0.08
    ifr
    -0.08
    åĽłä¸ºæĪij
    -0.08
    nage
    -0.08
    è¿Ļä¸Ģ次
    -0.08
    POSITIVE LOGITS
    å·²ä¹ħçļĦ
    0.11
     allegiance
    0.11
    ìķ¡
    0.10
    umper
    0.10
    edin
    0.09
    anst
    0.09
    otten
    0.09
     rằng
    0.09
    书
    0.09
    ño
    0.09
    Activations Density 0.003%

    No Known Activations