© 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. 7600
    Prev
    Next
    INDEX
    Explanations

    minor degree, variations, bug, earthquake, health, ities

    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
    soever
    -0.10
    ä¸įå®ī
    -0.09
    ses
    -0.09
    鸳
    -0.09
    anos
    -0.09
    oric
    -0.09
    ammen
    -0.09
    ë¥ł
    -0.09
    ils
    -0.09
    رÙģ
    -0.09
    POSITIVE LOGITS
    itized
    0.15
    mente
    0.11
    wares
    0.11
    itarian
    0.10
    -league
    0.10
    haps
    0.10
    theless
    0.09
    ish
    0.09
    est
    0.09
    ships
    0.09
    Activations Density 0.019%

    No Known Activations