© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 17211
    Prev
    Next
    INDEX
    Explanations

    daily events and activities

    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
    asti
    -0.09
    çļĦæĥħåĨµä¸ĭ
    -0.09
    obi
    -0.08
    ETO
    -0.08
    ourn
    -0.08
    \grid
    -0.08
     ÐŀÑĩ
    -0.08
    obil
    -0.08
    åĪĨ管
    -0.08
    iew
    -0.08
    POSITIVE LOGITS
    é¢ł
    0.10
     اÙĪ
    0.10
    ä»»ä½ķæŶåĢĻ
    0.09
    tool
    0.09
    ioni
    0.09
     or
    0.09
    loff
    0.09
     toolkit
    0.08
    lla
    0.08
    仲
    0.08
    Activations Density 0.057%

    No Known Activations