© 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. 53948
    Prev
    Next
    INDEX
    Explanations

    IMPORTANT or notice

    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
    æ¯Ķäºļ
    -0.10
    æŀŀ
    -0.09
    饱满
    -0.09
    æ¡ĪåŃIJ
    -0.09
    åħħè£ķ
    -0.08
    ä¸ĢåįĬ
    -0.08
     Klopp
    -0.08
    å¾Ī好
    -0.08
    åŁ
    -0.08
    å¾Īä¸įéĶĻ
    -0.08
    POSITIVE LOGITS
    åı¬
    0.10
    çģµéŃĤ
    0.09
    ä¼ī
    0.09
    éĹŃ
    0.08
    ÙĬاÙĨ
    0.08
    สาย
    0.08
    ç¨Ģ
    0.08
    irth
    0.08
    emy
    0.08
    .eng
    0.08
    Activations Density 0.050%

    No Known Activations