© 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. 27318
    Prev
    Next
    INDEX
    Explanations

    delete, b, aa, bool, content, Test

    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
    eer
    -0.08
    puter
    -0.08
    ripp
    -0.08
    å¹¶åľ¨
    -0.08
    LETE
    -0.07
    æijĺ
    -0.07
    Dyn
    -0.07
    çīĩ段
    -0.07
    æĪĸèĢħåħ¶ä»ĸ
    -0.07
    åħ¬å¼ĢæĭĽèģĺ
    -0.07
    POSITIVE LOGITS
    æľīä¿¡å¿ĥ
    0.09
    寮
    0.08
    峤
    0.08
    another
    0.08
    妩
    0.08
    åŁİåł¡
    0.08
    æľīä¸ĢçĤ¹
    0.07
    èĭ´
    0.07
    éĻ¤å¤ķ
    0.07
    æĤ¬å¿µ
    0.07
    Activations Density 0.259%

    No Known Activations