© 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. 8505
    Prev
    Next
    INDEX
    Explanations

    news sources

    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
    ters
    -0.11
    RARY
    -0.10
    zelf
    -0.09
    鸡
    -0.08
    å²ģæľĪ
    -0.08
    åķĨåĬ¡éĥ¨
    -0.08
    rary
    -0.08
    èļĵ
    -0.08
    ç£ĭ
    -0.08
    ate
    -0.08
    POSITIVE LOGITS
    flare
    0.11
    phin
    0.10
    letters
    0.10
    ocked
    0.10
    lero
    0.09
    สาร
    0.09
    rust
    0.09
    åı¯æĥľ
    0.09
    room
    0.09
    ÑĢон
    0.08
    Activations Density 0.032%

    No Known Activations