© 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. 37075
    Prev
    Next
    INDEX
    Explanations

    by chance or accident

    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
    æī¬
    -0.09
    èijĨ
    -0.09
    ç²¾ç¥ŀæĸĩæĺİ
    -0.09
    ä¾®
    -0.08
    èµĽåIJİ
    -0.08
    æĥĭ
    -0.08
    份
    -0.08
    akes
    -0.08
     lasers
    -0.08
    åħĥ
    -0.08
    POSITIVE LOGITS
    åģ¶çĦ¶
    0.13
    缸éģĩ
    0.11
    å·§åIJĪ
    0.10
    碰
    0.09
    æĢ§
    0.09
     ÑĥÑģпеÑħ
    0.09
    éĻħ
    0.09
    /random
    0.09
     whim
    0.09
    ngr
    0.08
    Activations Density 0.075%

    No Known Activations