© 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. 37169
    Prev
    Next
    INDEX
    Explanations

    sending emails or messages

    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
    mente
    -0.10
    ายà¸Ļ
    -0.10
    ety
    -0.10
    åįķåįķ
    -0.10
    çĶ¨éĩı
    -0.09
    iÄĻ
    -0.09
    cene
    -0.09
    mega
    -0.09
    ate
    -0.09
    è´²
    -0.09
    POSITIVE LOGITS
    OrUpdate
    0.11
    ToFront
    0.10
    ers
    0.10
    æĿ¥çļĦ
    0.10
    çĭIJ
    0.09
    /re
    0.09
    erset
    0.09
    ularity
    0.09
    rolled
    0.09
    recv
    0.09
    Activations Density 0.062%

    No Known Activations