© 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. 55243
    Prev
    Next
    INDEX
    Explanations

    .com websites

    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
    èľļ
    -0.10
    ä¹ĭ声
    -0.09
    æĭĴ
    -0.09
    æ¦ľ
    -0.09
    ä»ħ代表
    -0.09
    ansk
    -0.09
    æķijåij½
    -0.08
    轸
    -0.08
    æīįå¹²
    -0.08
    身边çļĦ
    -0.08
    POSITIVE LOGITS
    PIO
    0.09
    loyd
    0.09
    ä¸ĢæŃ¥
    0.09
    ghan
    0.09
    ê·Ģ
    0.08
    ä¸Ĭãģ®
    0.08
    é¢Ĭ
    0.08
    ctors
    0.08
    .oracle
    0.08
    VOKE
    0.08
    Activations Density 0.020%

    No Known Activations