© 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. 54590
    Prev
    Next
    INDEX
    Explanations

    "the accompanying materials"

    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
     {}.
    -0.10
    ç»ıéªĮåĴĮ
    -0.09
    è¿Ļæł·ä¸Ģ个
    -0.08
    éŃģ
    -0.08
    æĬĢæľ¯åĴĮ
    -0.08
     Dreams
    -0.08
    éĤ£ä¹Īç®Ģåįķ
    -0.08
    èĢĮä¸Ķè¿ĺ
    -0.08
    {}.
    -0.08
    ä¼ģä¸ļåĴĮ
    -0.08
    POSITIVE LOGITS
    ä¸Ģæł·
    0.11
    çļĦ人éĥ½
    0.11
    çħ§æł·
    0.10
    åĿĩ
    0.10
    éļıä¹ĭ
    0.10
    缸继
    0.10
    ä¸Ŀè·¯
    0.09
    erno
    0.09
    没åħ³ç³»
    0.09
    ä¸Ģèµ·
    0.09
    Activations Density 0.421%

    No Known Activations