© 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. 39255
    Prev
    Next
    INDEX
    Explanations

    north and east England

    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
    ä¸Ńæĸ¹
    -0.12
    OPY
    -0.10
    ä¸Ģ个éĩįè¦ģ
    -0.09
     пÑĥнкÑĤ
    -0.09
    ushman
    -0.09
    iling
    -0.09
    USTER
    -0.09
    ILLE
    -0.09
     Middleton
    -0.09
    并ä¸İ
    -0.09
    POSITIVE LOGITS
    nob
    0.09
    CAT
    0.09
    å¦Ĩ
    0.09
    èĿĻ
    0.08
    alt
    0.08
    è¯Ħå®ļ
    0.08
    é£İæļ´
    0.08
    å¾Ĥ
    0.08
    ifter
    0.08
     Stream
    0.08
    Activations Density 0.037%

    No Known Activations