© 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. 7674
    Prev
    Next
    INDEX
    Explanations

    binary form

    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
    enn
    -0.09
    /DD
    -0.08
    orian
    -0.08
    åīĬ
    -0.08
    anders
    -0.08
    ardin
    -0.08
    eeper
    -0.08
    ped
    -0.08
    lek
    -0.08
    (Of
    -0.08
    POSITIVE LOGITS
    桧
    0.11
    -binary
    0.10
    å¸ľ
    0.10
    åĮĸçļĦ
    0.10
    ç
    0.10
    IVES
    0.09
    /octet
    0.09
    (binary
    0.09
    emade
    0.09
    inary
    0.09
    Activations Density 0.067%

    No Known Activations