© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22337
    Prev
    Next
    INDEX
    Explanations

    fit in or into

    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
    棣
    -0.11
    ä¸įæľį
    -0.10
    Authority
    -0.10
    onaut
    -0.09
    éŃĥ
    -0.09
    bot
    -0.09
    å¿ĻçĿĢ
    -0.09
    lish
    -0.09
    诡
    -0.09
    BOT
    -0.09
    POSITIVE LOGITS
    æĮ¤
    0.16
    容纳
    0.14
     accommod
    0.10
    åħ¥
    0.10
    ãĤµãĤ¤ãĤº
    0.10
     accommodation
    0.10
    æĵł
    0.10
     помеÑī
    0.09
    诺
    0.09
    æĶ¾è¿Ľ
    0.09
    Activations Density 0.050%

    No Known Activations