© 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. 9541
    Prev
    Next
    INDEX
    Explanations

    make a statement

    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
    æĽĻåħī
    -0.09
    çĶ¨äºİ
    -0.09
    ìķł
    -0.09
    /apt
    -0.09
    æĹ¥çħ§
    -0.09
    ä¸Ń举
    -0.08
    åĢ©
    -0.08
    åıijæī¬
    -0.08
    uest
    -0.08
    uper
    -0.08
    POSITIVE LOGITS
    æĮĽ
    0.12
    åįģ足
    0.11
    å±ĭåŃIJ
    0.10
    antium
    0.09
     lawy
    0.09
    æĢ§å¼º
    0.09
    主ä¹īæĢĿæĥ³
    0.09
    京åŁİ
    0.09
    oji
    0.09
    æ²Ľ
    0.09
    Activations Density 0.006%

    No Known Activations