© 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. 54963
    Prev
    Next
    INDEX
    Explanations

    Country names and states

    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
    Kent
    -0.09
    åħ¨çIJĥæľĢ大
    -0.09
    KS
    -0.09
    iveau
    -0.09
    éªĬ
    -0.09
    otti
    -0.09
    éªĩ
    -0.08
    ä¹ĭä½Ļ
    -0.08
    uellement
    -0.08
     ISI
    -0.08
    POSITIVE LOGITS
     اÙĦÙĪاØŃد
    0.08
     Pvt
    0.08
    秾
    0.08
    对ä»ĸ们
    0.08
    çļĦ家åºŃ
    0.08
    çļĦæ¦Ĥ念
    0.08
    窳
    0.08
    饵
    0.08
    çļĦä¿¡å¿ĥ
    0.08
    åİ»åģļ
    0.07
    Activations Density 0.107%

    No Known Activations