© 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. 3011
    Prev
    Next
    INDEX
    Explanations

    Sri Lanka and Indian names

    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
    ukes
    -0.09
    iros
    -0.09
    è§ģè¯ģ
    -0.09
    壤
    -0.08
    isz
    -0.08
    illos
    -0.08
     counsel
    -0.08
    æѤåĪ»
    -0.08
     bapt
    -0.08
    hya
    -0.08
    POSITIVE LOGITS
    çģ¿çĥĤ
    0.10
    è¯Ķ
    0.10
    å¸ļ
    0.10
    èĢĢçľ¼
    0.10
     Everest
    0.10
    åĿIJçĿĢ
    0.09
    tractor
    0.09
    ä¸įæĸŃæıIJåįĩ
    0.09
     Lynn
    0.09
    æĤ«
    0.09
    Activations Density 0.054%

    No Known Activations