© 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. 31420
    Prev
    Next
    INDEX
    Explanations

    locations and proximity

    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
    owe
    -0.09
    oses
    -0.09
    Americ
    -0.09
    æīĵçĿĢ
    -0.09
    RID
    -0.09
     Everett
    -0.08
    çĮ´
    -0.08
    ixels
    -0.08
     Americas
    -0.08
    abo
    -0.08
    POSITIVE LOGITS
     sno
    0.10
    iment
    0.08
    icism
    0.08
    æł·æĿ¿
    0.08
    çļĦ好
    0.08
    ä¸įçŁ¥ä¸įè§ī
    0.08
    æ£ł
    0.08
    IOC
    0.08
    æĪIJçĨŁçļĦ
    0.08
    ä¸Ģ缴
    0.07
    Activations Density 0.162%

    No Known Activations