© 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. 17655
    Prev
    Next
    INDEX
    Explanations

    . Video

    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
    elman
    -0.10
    esting
    -0.10
    etur
    -0.09
    éĨ®
    -0.09
    ç§ī
    -0.09
    åľª
    -0.09
    äºĨä¸įå°ij
    -0.08
    SDK
    -0.08
    çĵ´
    -0.08
     gener
    -0.08
    POSITIVE LOGITS
    ãģĦãģĨ
    0.10
    èĿĩ
    0.09
    宽æĿ¾
    0.09
    istas
    0.09
    稳
    0.09
    æĪı
    0.09
    룬
    0.09
     Charlotte
    0.09
    lı
    0.09
    |required
    0.09
    Activations Density 0.003%

    No Known Activations