© 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. 37607
    Prev
    Next
    INDEX
    Explanations

    national park or state forest

    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
    Peripheral
    -0.10
    绶
    -0.10
    æ·«
    -0.10
    飬
    -0.09
    å¤ĸåĽ´
    -0.09
    å¼¥
    -0.09
    å²Ľ
    -0.09
    åĹ£
    -0.09
    bolt
    -0.09
    <decltype
    -0.09
    POSITIVE LOGITS
    æīĺ管
    0.09
    oes
    0.09
    å©Ĩ
    0.09
    è¾Ł
    0.09
     piece
    0.08
     lod
    0.08
    Wed
    0.08
    éĢ®
    0.08
    æĮļ
    0.08
    airo
    0.08
    Activations Density 0.098%

    No Known Activations