© 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. 61922
    Prev
    Next
    INDEX
    Explanations

    city and country 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
     Gerard
    -0.09
    ongs
    -0.09
    -0.08
     Shed
    -0.08
    omat
    -0.08
     acet
    -0.08
     UPC
    -0.08
     Lambert
    -0.08
    çħ¨
    -0.08
    ä¸İæѤ
    -0.07
    POSITIVE LOGITS
    åĪĨè¡Į
    0.10
    ç¯ĩ
    0.10
    ä¾ĽçĶµåħ¬åı¸
    0.09
    äºĶåħŃ
    0.08
    åĪĨå±Ģ
    0.08
    æĥħ趣
    0.08
    åĵ
    0.08
    èįª
    0.08
    .inst
    0.08
    èĤ¤
    0.08
    Activations Density 0.317%

    No Known Activations