© 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. 51697
    Prev
    Next
    INDEX
    Explanations

    born, followed by descriptions of origin

    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
    身形
    -0.10
    ÑīÑĥ
    -0.09
    bsites
    -0.09
    Ê°
    -0.09
    gn
    -0.09
    åijĺ
    -0.09
    建æĪIJåIJİ
    -0.09
    orts
    -0.09
    å¼Ģåĩº
    -0.09
    orian
    -0.08
    POSITIVE LOGITS
    OrUpdate
    0.11
    éĻħ
    0.10
    nings
    0.09
    enticated
    0.09
    ning
    0.09
    heimer
    0.09
    åij½åij¨æľŁ
    0.09
    rate
    0.09
     Dank
    0.09
    زÙĨ
    0.09
    Activations Density 0.060%

    No Known Activations