© 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. 49143
    Prev
    Next
    INDEX
    Explanations

    Austria and Austrian

    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
     hÆ°á»Łng
    -0.10
    ç¡ĸ
    -0.10
    åĦ¿
    -0.10
    åľ¯
    -0.09
    æı©
    -0.09
    åĽ½éĻħå¸Ĥåľº
    -0.09
    åħīèį£
    -0.08
    ä¸ŃåĽ½å¸Ĥåľº
    -0.08
    åıĮçľ¼
    -0.08
    èĭıèģĶ
    -0.08
    POSITIVE LOGITS
    /dom
    0.10
    grass
    0.10
    佬
    0.10
    ÑĪек
    0.09
    listed
    0.09
    iger
    0.09
    esser
    0.09
    çij¾
    0.09
    lander
    0.08
    reo
    0.08
    Activations Density 0.017%

    No Known Activations