© 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. 39721
    Prev
    Next
    INDEX
    Explanations

    money spent or saved

    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
     Malik
    -0.09
    å¼Ħ
    -0.09
    åıĤ
    -0.09
    继
    -0.09
     Wir
    -0.09
    çªľ
    -0.08
    Hosting
    -0.08
     Sidney
    -0.08
    æĶ¹éĢł
    -0.08
    èĬ¸
    -0.08
    POSITIVE LOGITS
    éĥijéĩį
    0.11
    çļĦæĬķèµĦ
    0.11
    é«ĺè´¨éĩı
    0.10
    æĬķèµĦ
    0.10
    é«ĺä»·
    0.10
    èĪįå¾Ĺ
    0.10
    主åĬ¨
    0.09
    éķ¿è¿ľ
    0.09
    æį¢æĿ¥
    0.09
    é«ĺæĺĤ
    0.09
    Activations Density 0.042%

    No Known Activations