© 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. 30981
    Prev
    Next
    INDEX
    Explanations

    wildlife and property descriptions

    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
    è²
    -0.10
    ÑĢÑĥб
    -0.09
    .metro
    -0.09
    ä¸įåłª
    -0.09
    åľ°çIJĥ
    -0.08
    è¸Ĭ
    -0.08
    nette
    -0.08
    éĺ²æ°´
    -0.08
     Philippines
    -0.08
    еп
    -0.08
    POSITIVE LOGITS
     Wyoming
    0.09
    åĪĨåĮº
    0.09
    åĽĽæĸ¹
    0.09
    鸢
    0.09
    çªĿ
    0.09
    红åĪ©
    0.09
    åĪĨ红
    0.09
     kenn
    0.09
    åĽ½æľī
    0.09
    åģļ大
    0.09
    Activations Density 0.060%

    No Known Activations