© 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. 2135
    Prev
    Next
    INDEX
    Explanations

    logistics

    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
    dio
    -0.10
    æľīæĿ¡ä»¶
    -0.10
    æºIJæºIJä¸įæĸŃ
    -0.09
    ../../../../
    -0.08
    IOD
    -0.08
    ãģ£ãģ±
    -0.08
    æĪij以为
    -0.08
    讳
    -0.08
    ../../../
    -0.08
    дÑĢ
    -0.08
    POSITIVE LOGITS
    廪
    0.10
    çĿ¬
    0.10
    íħĶ
    0.09
    ÙĬات
    0.09
    ivity
    0.09
    lek
    0.09
    ancock
    0.09
    æijĩ头
    0.08
    orget
    0.08
    èĿ¼
    0.08
    Activations Density 0.005%

    No Known Activations