© 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. 4232
    Prev
    Next
    INDEX
    Explanations

    speed-skating and Arduino boards

    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
    endant
    -0.09
    usty
    -0.09
    ä¹ħ
    -0.08
    _macros
    -0.08
    ç¼Ģ
    -0.08
    ryn
    -0.08
    à¹Ģà¸Īà¸Ń
    -0.08
    ä¸įåıĬ
    -0.07
     dock
    -0.07
    æŀĦ
    -0.07
    POSITIVE LOGITS
    æĸ°ä¸ļæĢģ
    0.12
    èĮĥ
    0.11
    æºħ
    0.10
    éķ±
    0.10
    urf
    0.09
    .rdf
    0.09
    çļĦéĢŁåº¦
    0.09
    æ»ijéĽª
    0.09
    梵
    0.09
    éĢŁåº¦
    0.08
    Activations Density 0.111%

    No Known Activations