© 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. 52986
    Prev
    Next
    INDEX
    Explanations

    fabulous nouns

    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
    zel
    -0.10
    ality
    -0.10
    soever
    -0.09
    opia
    -0.09
    åIJģ
    -0.09
    felt
    -0.09
    atology
    -0.09
    uitive
    -0.09
    esthetic
    -0.09
    o
    -0.09
    POSITIVE LOGITS
    ously
    0.09
    cope
    0.09
    ä¸ĢåĽ¢
    0.09
    anno
    0.09
    ous
    0.08
    /ext
    0.08
    ستر
    0.08
    ity
    0.08
    ibly
    0.08
    æ»Ķ
    0.08
    Activations Density 0.004%

    No Known Activations