© 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. 31288
    Prev
    Next
    INDEX
    Explanations

    object loop, iterative method, dynamic url, not generated

    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
    糧
    -0.10
    缮åīįæŃ£åľ¨
    -0.10
    æ¹ĺ
    -0.10
    åı¯ä¾Ľ
    -0.10
    æĪĸå°Ĩ
    -0.09
    èIJ½åľ°
    -0.09
    ä»»ä½ķå½¢å¼ı
    -0.09
    豪åįİ
    -0.09
    贯穿
    -0.09
    æ²ī
    -0.09
    POSITIVE LOGITS
    罪
    0.08
    éī
    0.08
    engan
    0.08
    è§ĩ
    0.08
    jam
    0.08
    çļĦçŃĶæ¡Ī
    0.08
    phanumeric
    0.08
    vio
    0.08
    æŸ
    0.08
    atest
    0.08
    Activations Density 0.005%

    No Known Activations