© 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. 11940
    Prev
    Next
    INDEX
    Explanations

    make appearances

    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
    åħ¼
    -0.10
    prüf
    -0.09
    ENTE
    -0.09
    çĶļ
    -0.09
    ommen
    -0.09
    没äºĨ
    -0.09
    tent
    -0.09
    пеÑĩ
    -0.08
    _hdl
    -0.08
    ç¼Ľ
    -0.08
    POSITIVE LOGITS
    èĩªæĪij
    0.10
    éĻ·
    0.10
    çݰ身
    0.09
    ä¸Ģ举
    0.09
    äº®çĽ¸
    0.09
    æĹ¶æľº
    0.09
    çij
    0.09
    æ·¹
    0.09
    为ä¸Ńå¿ĥ
    0.09
     rec
    0.09
    Activations Density 0.029%

    No Known Activations