© 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. 8353
    Prev
    Next
    INDEX
    Explanations

    names and short words like et

    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
    å©Ĩå©Ĩ
    -0.08
    åĢĴ
    -0.08
    奴
    -0.08
    CU
    -0.08
    éķ¿èĢģ
    -0.08
    ëĭ¤ëĬĶ
    -0.08
    æĺĢ
    -0.08
    ForMember
    -0.08
    CAP
    -0.08
    COME
    -0.08
    POSITIVE LOGITS
     et
    0.09
    æķĻä½ł
    0.09
    /stdc
    0.09
     prem
    0.09
    æĭ¿çĿĢ
    0.09
    è·Łä¸įä¸Ĭ
    0.08
    et
    0.08
     IMPLEMENT
    0.08
    çĩĥçħ¤
    0.08
    .sale
    0.08
    Activations Density 0.074%

    No Known Activations