© 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. 8159
    Prev
    Next
    INDEX
    Explanations

    hoping or hopes for the future

    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
    éħĮ
    -0.09
    æĽ²æĬĺ
    -0.09
    onn
    -0.09
    orm
    -0.09
    åİŁåĪĻä¸Ĭ
    -0.09
    uv
    -0.09
    åıªè§ģ
    -0.08
    Ñĥв
    -0.08
    çIJ¨
    -0.08
    ä¸įè§ģäºĨ
    -0.08
    POSITIVE LOGITS
    ÑĢеÑģ
    0.10
    .elem
    0.09
    稳
    0.09
    berger
    0.09
     ÃŃch
    0.09
    æijĨèĦ±
    0.08
     gì
    0.08
    neys
    0.08
    æĶ¯æŁ±
    0.08
    IBM
    0.08
    Activations Density 0.186%

    No Known Activations