© 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. 62569
    Prev
    Next
    INDEX
    Explanations

    close to

    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
    orer
    -0.10
    æĭĶ
    -0.09
    .unpack
    -0.09
    _td
    -0.09
    å±ĢéĻIJ
    -0.08
    æĬĵç´§
    -0.08
    æIJª
    -0.08
    æīī
    -0.08
    æľĢå¿«
    -0.08
    æ±Łæ¹ĸ
    -0.08
    POSITIVE LOGITS
    åı¯æĥľ
    0.11
    åį´è¢«
    0.11
    åĽ¾ä¸º
    0.10
    æľºä¼ļ
    0.09
     ÑģÑĤо
    0.09
    æĥĭ
    0.09
    victim
    0.09
    å¾Īæĥ³
    0.09
     otherwise
    0.09
     victim
    0.09
    Activations Density 0.048%

    No Known Activations