© 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. 21536
    Prev
    Next
    INDEX
    Explanations

    Japanese names ending in -san or -sama

    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
    аÑģÑģ
    -0.10
    è¦Ĩ
    -0.10
    è¿ĺ好
    -0.08
    ills
    -0.08
    rips
    -0.08
    Kel
    -0.08
    ç»ı纬
    -0.08
    artz
    -0.08
     australia
    -0.08
    ä¸Ģä½ĵ
    -0.07
    POSITIVE LOGITS
    ernaut
    0.09
    .orm
    0.09
    çĮľ
    0.09
    pak
    0.09
    殿åłĤ
    0.09
     ná»ģn
    0.09
    мÑĥ
    0.09
    å¹ķ
    0.08
    ä¸ĬçıŃæĹı
    0.08
    isoft
    0.08
    Activations Density 0.077%

    No Known Activations