© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10420
    Prev
    Next
    INDEX
    Explanations

    foreign carriers

    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
    åŁĶ
    -0.09
     Chase
    -0.08
    ardi
    -0.08
    ä¸Ģä¸Ŀ
    -0.08
     Dio
    -0.08
    zent
    -0.08
    æĴķ
    -0.08
    enet
    -0.08
    ä¸ĢçĤ¹éĥ½ä¸į
    -0.08
    ä¸Ģ声
    -0.08
    POSITIVE LOGITS
     Siber
    0.09
    æĺĿ
    0.09
    èķ¨
    0.09
    ivos
    0.09
    STATIC
    0.08
    icone
    0.08
    çĪ¸
    0.08
    æĪIJ为ä¸ŃåĽ½
    0.08
    éĺĻ
    0.08
    éĶº
    0.08
    Activations Density 0.334%

    No Known Activations