© 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. 49388
    Prev
    Next
    INDEX
    Explanations

    work and requirements

    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
    owie
    -0.10
    ä¸Ģåij³
    -0.08
    念
    -0.08
    åIJįå¸Ī
    -0.08
    åŃľ
    -0.08
    é¼»
    -0.08
    åħ·
    -0.08
    éĩįè¦ģæĦıä¹ī
    -0.08
    heck
    -0.08
    éĩįè¦ģåĽłç´ł
    -0.08
    POSITIVE LOGITS
    çķĻåľ¨
    0.10
    èĮ¨
    0.10
    done
    0.10
     done
    0.09
    æķ´å½¢
    0.09
    ä¸įå°½
    0.09
    夯å®ŀ
    0.09
    åĬŁè¯¾
    0.09
    ä¾Ŀæŧ
    0.09
    èĭĮ
    0.09
    Activations Density 0.016%

    No Known Activations