© 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. 8372
    Prev
    Next
    INDEX
    Explanations

    removal of

    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
    endon
    -0.09
    iesta
    -0.09
    CONS
    -0.09
    裤
    -0.09
    avis
    -0.09
    æ¯ĶåĪ©
    -0.09
    CLUS
    -0.09
    ç¿ķ
    -0.09
    egra
    -0.09
    è£Ĥ
    -0.08
    POSITIVE LOGITS
    åıĸåĩº
    0.15
    åĩºæĿ¥
    0.14
    äºĨåĩºæĿ¥
    0.12
    åĩºæĿ¥äºĨ
    0.11
    æĭ¿åĩºæĿ¥
    0.11
    åĩºä¾Ĩ
    0.11
    ä¸įåĩºæĿ¥
    0.11
    åĩºçĤī
    0.10
    赡
    0.10
    åĩºãģĻ
    0.10
    Activations Density 0.127%

    No Known Activations