© 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. 39783
    Prev
    Next
    INDEX
    Explanations

    energy, space, numbers, dates, acronyms

    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
    å«¡
    -0.10
    æľºåĪ¶
    -0.09
    游ä¹IJ
    -0.09
    奥巴
    -0.09
    udu
    -0.09
    çĶŁäº§è®¾å¤ĩ
    -0.09
    _SETTING
    -0.09
     repar
    -0.08
    æĸ°éĹ»ä¸Ńå¿ĥ
    -0.08
    èĢģé¾Ħ
    -0.08
    POSITIVE LOGITS
    æ±Ĺ
    0.13
    常年
    0.10
    лоÑģÑĮ
    0.10
    è¿Ľé©»
    0.09
    å¥ī
    0.09
    裸
    0.08
    èľ¥
    0.08
    æIJ¬
    0.08
    æ±
    0.08
     rack
    0.08
    Activations Density 0.092%

    No Known Activations