© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19954
    Prev
    Next
    INDEX
    Explanations

    software or legal text

    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
    è¿Ļæł·æīįèĥ½
    -0.09
    åįķ纯çļĦ
    -0.08
    éŀ
    -0.08
    éªĿ
    -0.08
    coh
    -0.08
    IDX
    -0.08
    abbr
    -0.08
    \xb
    -0.08
    ushman
    -0.08
    è¿Ļ件
    -0.08
    POSITIVE LOGITS
    âĢIJ
    0.09
    æķ´ä¸ª
    0.09
    .design
    0.08
    åħĪæĺ¯
    0.08
    yük
    0.08
    \/\/
    0.08
     \<^
    0.08
    åħ¶å®ŀ
    0.08
    åį³æŶåıijçĶŁ
    0.08
    essler
    0.08
    Activations Density 2.934%

    No Known Activations