© 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. 30524
    Prev
    Next
    INDEX
    Explanations

    camera and emission computed scintigraphy

    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
    Unlock
    -0.09
    èĭĩ
    -0.09
    èį«
    -0.09
    neau
    -0.09
    èĮ§
    -0.08
    aug
    -0.08
    æĭĮ
    -0.08
    è§īå¾Ĺ
    -0.08
    çªģå¦Ĥåħ¶æĿ¥
    -0.08
    åĺ¶
    -0.08
    POSITIVE LOGITS
    ç½ijç«Ļåľ°åĽ¾
    0.12
    æĤ¼
    0.10
    éĻIJ度
    0.09
    æĢĢæĬ±
    0.09
    饿
    0.09
    åĪ«
    0.08
    uten
    0.08
    åºĶæĶ¶
    0.08
     reim
    0.08
    æĸĩåĮĸçļĦ
    0.08
    Activations Density 0.468%

    No Known Activations