© 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. 8681
    Prev
    Next
    INDEX
    Explanations

    file extensions (.pdf, .jpg, .png, .bib, .tex)

    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
    xmm
    -0.10
    /github
    -0.10
     Hen
    -0.09
    WRAPPER
    -0.09
    AdapterManager
    -0.09
    å®ĺæĸ¹å¾®åįļ
    -0.09
    /rs
    -0.09
    æĭŃ
    -0.09
     Теп
    -0.08
    âĪİ
    -0.08
    POSITIVE LOGITS
    .pdf
    0.12
    _
    0.11
    .tex
    0.09
    æĪijä¸į
    0.08
    ä»ĸ们éĥ½
    0.08
    æĬĹæĭĴ
    0.08
    .jpg
    0.08
    B
    0.08
    åī¯æľ¬
    0.08
    ä¸įåľ¨ä¹İ
    0.08
    Activations Density 0.476%

    No Known Activations