© 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. 30486
    Prev
    Next
    INDEX
    Explanations

    look at / examine

    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
     scram
    -0.10
    åıĤèĢĥèµĦæĸĻ
    -0.10
    çŁ³åĮĸ
    -0.10
    åĽŀè´Ń
    -0.09
    /md
    -0.08
    ä¸Ģ声
    -0.08
    å·
    -0.08
    AAF
    -0.08
    oor
    -0.08
    (reader
    -0.08
    POSITIVE LOGITS
    å¦Ĥä½ķ
    0.12
    å¦Ĥä½ķåİ»
    0.10
     how
    0.10
    çļĦå°±æĺ¯
    0.09
    éģİåİ»
    0.09
    hoe
    0.09
    è¿ĩåİ»
    0.09
    æĭ¿
    0.09
    æĸ¥
    0.09
     factors
    0.08
    Activations Density 0.052%

    No Known Activations