© 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. 8384
    Prev
    Next
    INDEX
    Explanations

    url parameters and UTM codes

    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
    ä¸İä¸ŃåĽ½
    -0.10
    omet
    -0.09
    åĽ«
    -0.09
     thả
    -0.09
    itions
    -0.09
    京津
    -0.08
    éĺIJéĩĬ
    -0.08
    模仿
    -0.08
    .invoke
    -0.08
    umo
    -0.08
    POSITIVE LOGITS
    åĬ¡
    0.09
     CIS
    0.09
    æ»
    0.08
    请æķĻ
    0.08
    .Scan
    0.08
    NSS
    0.08
    icie
    0.08
    bez
    0.08
    -php
    0.08
    åħĦå¼Ł
    0.08
    Activations Density 0.061%

    No Known Activations