© 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. 2987
    Prev
    Next
    INDEX
    Explanations

    Paul's, Quorn, Flipboard, allycar

    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
    boro
    -0.09
    漫éķ¿
    -0.09
    红éħĴ
    -0.09
    å²±
    -0.09
    çģ«çĤ¬
    -0.09
    æªĢ
    -0.08
    åĢ¡
    -0.08
     minut
    -0.08
    åħ¬åŃIJ
    -0.08
    åIJĮåŁİ
    -0.08
    POSITIVE LOGITS
    çIJĨæĥ³
    0.10
    å¸Ľ
    0.10
    wyn
    0.09
    opsy
    0.09
    øy
    0.09
    âĮľ
    0.08
     Zy
    0.08
    à¸Ńม
    0.08
    _PG
    0.08
    ëıĪ
    0.08
    Activations Density 0.001%

    No Known Activations