© 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. 62154
    Prev
    Next
    INDEX
    Explanations

    towns and locations in 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
    enko
    -0.09
     Winnipeg
    -0.09
    ä»ģ
    -0.08
    æIJª
    -0.08
    è¾½å®ģçľģ
    -0.08
    çķ´
    -0.08
    è¾½
    -0.08
    operand
    -0.08
    æłª
    -0.08
    æĿµ
    -0.08
    POSITIVE LOGITS
    _ERRORS
    0.11
     Southampton
    0.11
    ODEV
    0.10
    æ´¹
    0.10
    ç¼Ļ
    0.10
     Hampshire
    0.10
    lime
    0.09
    ictionaries
    0.09
    éĿŀè¦ģ
    0.09
     GAR
    0.09
    Activations Density 0.089%

    No Known Activations