© 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. 22883
    Prev
    Next
    INDEX
    Explanations

    Barry followed by name or place

    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
    ally
    -0.10
    欢è¿İæĤ¨
    -0.10
    ALLY
    -0.10
    åİŁåĽłä¹ĭä¸Ģ
    -0.09
     dyn
    -0.09
     Leer
    -0.09
    enic
    -0.09
    ãģĹãģ¾ãģĦ
    -0.09
    -child
    -0.09
    itr
    -0.09
    POSITIVE LOGITS
     Ñģобой
    0.11
    ../../
    0.11
    atchet
    0.10
    sburg
    0.09
    TURE
    0.09
    wayne
    0.09
    èĤļ
    0.09
    oque
    0.09
    ses
    0.09
     cú
    0.09
    Activations Density 0.006%

    No Known Activations