© 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. 61786
    Prev
    Next
    INDEX
    Explanations

    see

    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
    èģª
    -0.10
    /lic
    -0.10
    纯åĩĢ
    -0.10
    饯
    -0.09
    æįIJèµł
    -0.09
    ãģ©ãģĨãģĹãģ¦ãĤĤ
    -0.09
    对æĪijæĿ¥è¯´
    -0.09
     Hosp
    -0.09
    çģµéŃĤ
    -0.09
    åħ·ä½ĵçļĦ
    -0.09
    POSITIVE LOGITS
     plenty
    0.11
     przecież
    0.10
    çħ§æł·
    0.10
    éļ¾éģĵ
    0.10
    ãģłãģ£ãģ¦
    0.10
    ä¹Łæľīå¾Īå¤ļ
    0.09
    å¾Īå¤ļ
    0.09
    å®Įåħ¨åı¯ä»¥
    0.09
    åıįèĢĮ
    0.09
    æĪIJçĨŁçļĦ
    0.09
    Activations Density 0.105%

    No Known Activations