© 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. 19905
    Prev
    Next
    INDEX
    Explanations

    old place names or descriptions

    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
    кон
    -0.09
    å®ŀä¹łçĶŁ
    -0.09
    åIJĥçļĦ
    -0.09
    纤维
    -0.09
    çļĸ
    -0.09
    éĩijåŃĹå¡Ķ
    -0.08
    å³°åĢ¼
    -0.08
    å°ıä¼Ļ
    -0.08
    odesk
    -0.08
    IVEN
    -0.08
    POSITIVE LOGITS
    æŧ
    0.09
    èĪĬ
    0.09
    åı¤
    0.09
    åĬŁåĬĽ
    0.09
    slashes
    0.08
    Old
    0.08
    æĨ§
    0.08
    servers
    0.08
    yers
    0.08
     Hands
    0.08
    Activations Density 0.028%

    No Known Activations